Spaces:
Sleeping
Sleeping
Deploy tested PureCipher build 5bd407c3b7812ee3596ef0e1eea9afa5ecff0534
Browse files- .cursor/rules/core-mcp-objects.mdc +0 -13
- .gitattributes +2 -0
- .github/copilot-instructions.md +0 -1
- AGENTS.md +0 -251
- CLAUDE.md +0 -1
- CODE_OF_CONDUCT.md +0 -128
- README.md +3 -3
- README_OPENAPI.md +0 -246
- Windows_Notes.md +0 -58
- build.json +2 -2
- docs/.cursor/rules/mintlify.mdc +0 -364
- docs/REFLEXIVE_CORE_WHITEPAPER.md +0 -633
- index.html +3 -3
- wheels/{fastmcp-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp-0.0.1.dev4090+5bd407c3-py3-none-any.whl} +2 -2
- wheels/{fastmcp_remote-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp_remote-0.0.1.dev4090+5bd407c3-py3-none-any.whl} +0 -0
- wheels/{fastmcp_slim-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp_slim-0.0.1.dev4090+5bd407c3-py3-none-any.whl} +2 -2
- wheels/{fastmcp_tasks-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp_tasks-0.0.1.dev4090+5bd407c3-py3-none-any.whl} +0 -0
.cursor/rules/core-mcp-objects.mdc
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
description:
|
| 3 |
-
globs:
|
| 4 |
-
alwaysApply: true
|
| 5 |
-
---
|
| 6 |
-
There are four major MCP object types:
|
| 7 |
-
|
| 8 |
-
- Tools (src/tools/)
|
| 9 |
-
- Resources (src/resources/)
|
| 10 |
-
- Resource Templates (src/resources/)
|
| 11 |
-
- Prompts (src/prompts)
|
| 12 |
-
|
| 13 |
-
While these have slightly different semantics and implementations, in general changes that affect interactions with any one (like adding tags, importing, etc.) will need to be adopted, applied, and tested on all others. Be sure to look at not only the object definition but also the related `Manager` (e.g. `ToolManager`, `ResourceManager`, and `PromptManager`). Also note that while resources and resource templates are different objects, they both are handled by the `ResourceManager`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.gitattributes
CHANGED
|
@@ -9,3 +9,5 @@ wheels/fastmcp-0.0.1.dev4087+67f290ef-py3-none-any.whl filter=lfs diff=lfs merge
|
|
| 9 |
wheels/fastmcp_slim-0.0.1.dev4087+67f290ef-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
| 10 |
wheels/fastmcp-0.0.1.dev4088+b8f75f12-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
| 11 |
wheels/fastmcp_slim-0.0.1.dev4088+b8f75f12-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 9 |
wheels/fastmcp_slim-0.0.1.dev4087+67f290ef-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
| 10 |
wheels/fastmcp-0.0.1.dev4088+b8f75f12-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
| 11 |
wheels/fastmcp_slim-0.0.1.dev4088+b8f75f12-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
wheels/fastmcp-0.0.1.dev4090+5bd407c3-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
wheels/fastmcp_slim-0.0.1.dev4090+5bd407c3-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
.github/copilot-instructions.md
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
../AGENTS.md
|
|
|
|
|
|
AGENTS.md
DELETED
|
@@ -1,251 +0,0 @@
|
|
| 1 |
-
# FastMCP Development Guidelines
|
| 2 |
-
|
| 3 |
-
> **Audience**: LLM-driven engineering agents and human developers
|
| 4 |
-
|
| 5 |
-
FastMCP is a comprehensive Python framework (Python ≥3.10) for building Model Context Protocol (MCP) servers and clients. This is the actively maintained v2.0 providing a complete toolkit for the MCP ecosystem.
|
| 6 |
-
|
| 7 |
-
## Required Development Workflow
|
| 8 |
-
|
| 9 |
-
**CRITICAL**: Always run these commands in sequence before committing:
|
| 10 |
-
|
| 11 |
-
```bash
|
| 12 |
-
uv sync # Install dependencies
|
| 13 |
-
uv run pre-commit run --all-files # Ruff + Prettier + ty
|
| 14 |
-
uv run pytest # Run full test suite
|
| 15 |
-
```
|
| 16 |
-
|
| 17 |
-
**All three must pass** - this is enforced by CI. Alternative: `just build && just typecheck && just test`
|
| 18 |
-
|
| 19 |
-
**Tests must pass and lint/typing must be clean before committing.**
|
| 20 |
-
|
| 21 |
-
## Repository Structure
|
| 22 |
-
|
| 23 |
-
| Path | Purpose |
|
| 24 |
-
| ---------------- | ------------------------------------------------------ |
|
| 25 |
-
| `src/fastmcp/` | Library source code (Python ≥ 3.10) |
|
| 26 |
-
| `├─server/` | Server implementation, `FastMCP`, auth, networking |
|
| 27 |
-
| `│ ├─auth/` | Authentication providers (Bearer, JWT, WorkOS) |
|
| 28 |
-
| `│ └─middleware/` | Error handling, logging, rate limiting |
|
| 29 |
-
| `├─client/` | High-level client SDK + transports |
|
| 30 |
-
| `│ └─auth/` | Client authentication (Bearer, OAuth) |
|
| 31 |
-
| `├─tools/` | Tool implementations + `ToolManager` |
|
| 32 |
-
| `├─resources/` | Resources, templates + `ResourceManager` |
|
| 33 |
-
| `├─prompts/` | Prompt templates + `PromptManager` |
|
| 34 |
-
| `├─cli/` | FastMCP CLI commands (`run`, `dev`, `install`) |
|
| 35 |
-
| `├─contrib/` | Community contributions (bulk caller, mixins) |
|
| 36 |
-
| `├─experimental/` | Experimental features (new OpenAPI parser) |
|
| 37 |
-
| `└─utilities/` | Shared utilities (logging, JSON schema, HTTP) |
|
| 38 |
-
| `tests/` | Comprehensive pytest suite with markers |
|
| 39 |
-
| `docs/` | Mintlify documentation (published to gofastmcp.com) |
|
| 40 |
-
| `examples/` | Runnable demo servers (echo, smart_home, atproto) |
|
| 41 |
-
|
| 42 |
-
## Core MCP Objects
|
| 43 |
-
|
| 44 |
-
When modifying MCP functionality, changes typically need to be applied across all object types:
|
| 45 |
-
|
| 46 |
-
- **Tools** (`src/tools/` + `ToolManager`)
|
| 47 |
-
- **Resources** (`src/resources/` + `ResourceManager`)
|
| 48 |
-
- **Resource Templates** (`src/resources/` + `ResourceManager`)
|
| 49 |
-
- **Prompts** (`src/prompts/` + `PromptManager`)
|
| 50 |
-
|
| 51 |
-
## Testing Best Practices
|
| 52 |
-
|
| 53 |
-
### Testing Standards
|
| 54 |
-
|
| 55 |
-
- Every test: atomic, self-contained, single functionality
|
| 56 |
-
- Use parameterization for multiple examples of same functionality
|
| 57 |
-
- Use separate tests for different functionality pieces
|
| 58 |
-
- Put imports at the top of the file, not in the test body
|
| 59 |
-
- **NEVER** add `@pytest.mark.asyncio` to tests - `asyncio_mode = "auto"` is set globally
|
| 60 |
-
- **ALWAYS** run pytest after significant changes
|
| 61 |
-
|
| 62 |
-
### Always Use In-Memory Transport
|
| 63 |
-
|
| 64 |
-
Pass FastMCP servers directly to clients for testing:
|
| 65 |
-
|
| 66 |
-
```python
|
| 67 |
-
mcp = FastMCP("TestServer")
|
| 68 |
-
|
| 69 |
-
@mcp.tool
|
| 70 |
-
def greet(name: str) -> str:
|
| 71 |
-
return f"Hello, {name}!"
|
| 72 |
-
|
| 73 |
-
# Direct connection - no network complexity
|
| 74 |
-
async with Client(mcp) as client:
|
| 75 |
-
result = await client.call_tool("greet", {"name": "World"})
|
| 76 |
-
```
|
| 77 |
-
|
| 78 |
-
Only use HTTP transport when explicitly testing network features:
|
| 79 |
-
|
| 80 |
-
```python
|
| 81 |
-
# Network testing only
|
| 82 |
-
async with Client(transport=StreamableHttpTransport(server_url)) as client:
|
| 83 |
-
result = await client.ping()
|
| 84 |
-
```
|
| 85 |
-
|
| 86 |
-
## Development Rules
|
| 87 |
-
|
| 88 |
-
### Git & CI
|
| 89 |
-
|
| 90 |
-
- Pre-commit hooks are required (run automatically on commits)
|
| 91 |
-
- Never amend commits to fix pre-commit failures
|
| 92 |
-
- Apply PR labels: bugs/breaking/enhancements/features
|
| 93 |
-
- Improvements = enhancements (not features) unless specified
|
| 94 |
-
- **NEVER** force-push on collaborative repos
|
| 95 |
-
- **ALWAYS** run pre-commit before PRs
|
| 96 |
-
|
| 97 |
-
### Commit Messages and Agent Attribution
|
| 98 |
-
|
| 99 |
-
- **Agents NOT acting on behalf of @jlowin MUST identify themselves** (e.g., "🤖 Generated with Claude Code" in commits/PRs)
|
| 100 |
-
- Keep commit messages brief - ideally just headlines, not detailed messages
|
| 101 |
-
- Focus on what changed, not how or why
|
| 102 |
-
- Always read issue comments for follow-up information (treat maintainers as authoritative)
|
| 103 |
-
|
| 104 |
-
### PR Messages - Required Structure
|
| 105 |
-
|
| 106 |
-
- 1-2 paragraphs: problem/tension + solution (PRs are documentation!)
|
| 107 |
-
- Focused code example showing key capability
|
| 108 |
-
- **Avoid:** bullet summaries, exhaustive change lists, verbose closes/fixes, marketing language
|
| 109 |
-
- **Do:** Be opinionated about why change matters, show before/after scenarios
|
| 110 |
-
- Minor fixes: keep body short and concise
|
| 111 |
-
- No "test plan" sections or testing summaries
|
| 112 |
-
|
| 113 |
-
### Code Standards
|
| 114 |
-
|
| 115 |
-
- Python ≥ 3.10 with full type annotations
|
| 116 |
-
- Follow existing patterns and maintain consistency
|
| 117 |
-
- **Prioritize readable, understandable code** - clarity over cleverness
|
| 118 |
-
- Avoid obfuscated or confusing patterns even if they're shorter
|
| 119 |
-
- Use `# type: ignore[attr-defined]` in tests for MCP results instead of type assertions
|
| 120 |
-
- Each feature needs corresponding tests
|
| 121 |
-
|
| 122 |
-
### Documentation
|
| 123 |
-
|
| 124 |
-
- Uses Mintlify framework
|
| 125 |
-
- Files must be in docs.json to be included
|
| 126 |
-
- Never modify `docs/python-sdk/**` (auto-generated)
|
| 127 |
-
- **Core Principle:** A feature doesn't exist unless it is documented!
|
| 128 |
-
|
| 129 |
-
### Documentation Guidelines
|
| 130 |
-
|
| 131 |
-
- **Code Examples:** Explain before showing code, make blocks fully runnable (include imports)
|
| 132 |
-
- **Structure:** Headers form navigation guide, logical H2/H3 hierarchy
|
| 133 |
-
- **Content:** User-focused sections, motivate features (why) before mechanics (how)
|
| 134 |
-
- **Style:** Prose over code comments for important information
|
| 135 |
-
|
| 136 |
-
## Code Review Guidelines
|
| 137 |
-
|
| 138 |
-
### Philosophy
|
| 139 |
-
|
| 140 |
-
Code review is about maintaining a healthy codebase while helping contributors succeed. The burden of proof is on the PR to demonstrate it adds value in the intended way. Your job is to help it get there through actionable feedback.
|
| 141 |
-
|
| 142 |
-
**Critical**: A perfectly written PR that adds unwanted functionality must still be rejected. The code must advance the codebase in the intended direction, not just be well-written. When rejecting, provide clear guidance on how to align with project goals.
|
| 143 |
-
|
| 144 |
-
Be friendly and welcoming while maintaining high standards. Call out what works well - this reinforces good patterns. When code needs improvement, be specific about why and how to fix it. Remember that PRs serve as documentation for future developers.
|
| 145 |
-
|
| 146 |
-
### Focus On
|
| 147 |
-
|
| 148 |
-
- **Does this advance the codebase in the intended direction?** (Even perfect code for unwanted features should be rejected)
|
| 149 |
-
- **API design and naming clarity** - Identify confusing patterns (e.g., parameter values that contradict defaults) or non-idiomatic code (mutable defaults, etc.). Contributed code will need to be maintained indefinitely, and by someone other than the author (unless the author is a maintainer).
|
| 150 |
-
- **Suggest specific improvements**, not generic "add more tests" comments
|
| 151 |
-
- **Think about API ergonomics and learning curve** from a user perspective
|
| 152 |
-
|
| 153 |
-
### For Agent Reviewers
|
| 154 |
-
|
| 155 |
-
- **Read the full context**: Always examine related files, tests, and documentation before reviewing
|
| 156 |
-
- **Check against established patterns**: Look for consistency with existing codebase conventions
|
| 157 |
-
- **Verify functionality claims**: Don't just read code - understand what it actually does
|
| 158 |
-
- **Consider edge cases**: Think through error conditions and boundary scenarios
|
| 159 |
-
|
| 160 |
-
### Avoid
|
| 161 |
-
|
| 162 |
-
- Generic feedback without specifics
|
| 163 |
-
- Hypothetical problems unlikely to occur
|
| 164 |
-
- Nitpicking organizational choices without strong reason
|
| 165 |
-
- Summarizing what the PR already describes
|
| 166 |
-
- Star ratings or excessive emojis
|
| 167 |
-
- Bikeshedding style preferences when functionality is correct
|
| 168 |
-
- Requesting changes without suggesting solutions
|
| 169 |
-
- Focusing on personal coding style over project conventions
|
| 170 |
-
|
| 171 |
-
### Tone
|
| 172 |
-
|
| 173 |
-
- Acknowledge good decisions ("This API design is clean")
|
| 174 |
-
- Be direct but respectful
|
| 175 |
-
- Explain impact ("This will confuse users because...")
|
| 176 |
-
- Remember: Someone else maintains this code forever
|
| 177 |
-
|
| 178 |
-
### Decision Framework
|
| 179 |
-
|
| 180 |
-
Before approving, ask yourself:
|
| 181 |
-
|
| 182 |
-
1. Does this PR achieve its stated purpose?
|
| 183 |
-
2. Is that purpose aligned with where the codebase should go?
|
| 184 |
-
3. Would I be comfortable maintaining this code?
|
| 185 |
-
4. Have I actually understood what it does, not just what it claims?
|
| 186 |
-
5. Does this change introduce technical debt?
|
| 187 |
-
|
| 188 |
-
If something needs work, your review should help it get there through specific, actionable feedback. If it's solving the wrong problem, say so clearly.
|
| 189 |
-
|
| 190 |
-
### Review Comment Examples
|
| 191 |
-
|
| 192 |
-
**Good Review Comments:**
|
| 193 |
-
|
| 194 |
-
❌ "Add more tests"
|
| 195 |
-
✅ "The `handle_timeout` method needs tests for the edge case where timeout=0"
|
| 196 |
-
|
| 197 |
-
❌ "This API is confusing"
|
| 198 |
-
✅ "The parameter name `data` is ambiguous - consider `message_content` to match the MCP specification"
|
| 199 |
-
|
| 200 |
-
❌ "This could be better"
|
| 201 |
-
✅ "This approach works but creates a circular dependency. Consider moving the validation to `utils/validators.py`"
|
| 202 |
-
|
| 203 |
-
### Review Checklist
|
| 204 |
-
|
| 205 |
-
Before approving, verify:
|
| 206 |
-
- [ ] All required development workflow steps completed (uv sync, pre-commit, pytest)
|
| 207 |
-
- [ ] Changes align with repository patterns and conventions
|
| 208 |
-
- [ ] API changes are documented and backwards-compatible where possible
|
| 209 |
-
- [ ] Error handling follows project patterns (specific exception types)
|
| 210 |
-
- [ ] Tests cover new functionality and edge cases
|
| 211 |
-
|
| 212 |
-
## Key Tools & Commands
|
| 213 |
-
|
| 214 |
-
### Environment Setup
|
| 215 |
-
|
| 216 |
-
```bash
|
| 217 |
-
git clone <repo>
|
| 218 |
-
cd fastmcp
|
| 219 |
-
uv sync # Installs all deps including dev tools
|
| 220 |
-
```
|
| 221 |
-
|
| 222 |
-
### Validation Commands (Run Frequently)
|
| 223 |
-
|
| 224 |
-
- **Linting**: `uv run ruff check` (or with `--fix`)
|
| 225 |
-
- **Type Checking**: `uv run ty check`
|
| 226 |
-
- **All Checks**: `uv run pre-commit run --all-files`
|
| 227 |
-
|
| 228 |
-
### Testing
|
| 229 |
-
|
| 230 |
-
- **Standard**: `uv run pytest`
|
| 231 |
-
- **Integration**: `uv run pytest -m "integration"`
|
| 232 |
-
- **Excluding markers**: `uv run pytest -m "not integration and not client_process"`
|
| 233 |
-
|
| 234 |
-
### CLI Usage
|
| 235 |
-
|
| 236 |
-
- **Run server**: `uv run fastmcp run server.py`
|
| 237 |
-
- **Inspect server**: `uv run fastmcp inspect server.py`
|
| 238 |
-
|
| 239 |
-
## Critical Patterns
|
| 240 |
-
|
| 241 |
-
### Error Handling
|
| 242 |
-
|
| 243 |
-
- Never use bare `except` - be specific with exception types
|
| 244 |
-
- Use `# type: ignore[attr-defined]` in tests for MCP results
|
| 245 |
-
|
| 246 |
-
### Build Issues (Common Solutions)
|
| 247 |
-
|
| 248 |
-
1. **Dependencies**: Always `uv sync` first
|
| 249 |
-
2. **Pre-commit fails**: Run `uv run pre-commit run --all-files` to see failures
|
| 250 |
-
3. **Type errors**: Use `uv run ty check` directly, check `pyproject.toml` config
|
| 251 |
-
4. **Test timeouts**: Default 3s - optimize or mark as integration tests
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
CLAUDE.md
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
AGENTS.md
|
|
|
|
|
|
CODE_OF_CONDUCT.md
DELETED
|
@@ -1,128 +0,0 @@
|
|
| 1 |
-
# Contributor Covenant Code of Conduct
|
| 2 |
-
|
| 3 |
-
## Our Pledge
|
| 4 |
-
|
| 5 |
-
We as members, contributors, and leaders pledge to make participation in our
|
| 6 |
-
community a harassment-free experience for everyone, regardless of age, body
|
| 7 |
-
size, visible or invisible disability, ethnicity, sex characteristics, gender
|
| 8 |
-
identity and expression, level of experience, education, socio-economic status,
|
| 9 |
-
nationality, personal appearance, race, religion, or sexual identity
|
| 10 |
-
and orientation.
|
| 11 |
-
|
| 12 |
-
We pledge to act and interact in ways that contribute to an open, welcoming,
|
| 13 |
-
diverse, inclusive, and healthy community.
|
| 14 |
-
|
| 15 |
-
## Our Standards
|
| 16 |
-
|
| 17 |
-
Examples of behavior that contributes to a positive environment for our
|
| 18 |
-
community include:
|
| 19 |
-
|
| 20 |
-
* Demonstrating empathy and kindness toward other people
|
| 21 |
-
* Being respectful of differing opinions, viewpoints, and experiences
|
| 22 |
-
* Giving and gracefully accepting constructive feedback
|
| 23 |
-
* Accepting responsibility and apologizing to those affected by our mistakes,
|
| 24 |
-
and learning from the experience
|
| 25 |
-
* Focusing on what is best not just for us as individuals, but for the
|
| 26 |
-
overall community
|
| 27 |
-
|
| 28 |
-
Examples of unacceptable behavior include:
|
| 29 |
-
|
| 30 |
-
* The use of sexualized language or imagery, and sexual attention or
|
| 31 |
-
advances of any kind
|
| 32 |
-
* Trolling, insulting or derogatory comments, and personal or political attacks
|
| 33 |
-
* Public or private harassment
|
| 34 |
-
* Publishing others' private information, such as a physical or email
|
| 35 |
-
address, without their explicit permission
|
| 36 |
-
* Other conduct which could reasonably be considered inappropriate in a
|
| 37 |
-
professional setting
|
| 38 |
-
|
| 39 |
-
## Enforcement Responsibilities
|
| 40 |
-
|
| 41 |
-
Community leaders are responsible for clarifying and enforcing our standards of
|
| 42 |
-
acceptable behavior and will take appropriate and fair corrective action in
|
| 43 |
-
response to any behavior that they deem inappropriate, threatening, offensive,
|
| 44 |
-
or harmful.
|
| 45 |
-
|
| 46 |
-
Community leaders have the right and responsibility to remove, edit, or reject
|
| 47 |
-
comments, commits, code, wiki edits, issues, and other contributions that are
|
| 48 |
-
not aligned to this Code of Conduct, and will communicate reasons for moderation
|
| 49 |
-
decisions when appropriate.
|
| 50 |
-
|
| 51 |
-
## Scope
|
| 52 |
-
|
| 53 |
-
This Code of Conduct applies within all community spaces, and also applies when
|
| 54 |
-
an individual is officially representing the community in public spaces.
|
| 55 |
-
Examples of representing our community include using an official e-mail address,
|
| 56 |
-
posting via an official social media account, or acting as an appointed
|
| 57 |
-
representative at an online or offline event.
|
| 58 |
-
|
| 59 |
-
## Enforcement
|
| 60 |
-
|
| 61 |
-
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
| 62 |
-
reported to the community leaders responsible for enforcement at
|
| 63 |
-
chris@prefect.io.
|
| 64 |
-
All complaints will be reviewed and investigated promptly and fairly.
|
| 65 |
-
|
| 66 |
-
All community leaders are obligated to respect the privacy and security of the
|
| 67 |
-
reporter of any incident.
|
| 68 |
-
|
| 69 |
-
## Enforcement Guidelines
|
| 70 |
-
|
| 71 |
-
Community leaders will follow these Community Impact Guidelines in determining
|
| 72 |
-
the consequences for any action they deem in violation of this Code of Conduct:
|
| 73 |
-
|
| 74 |
-
### 1. Correction
|
| 75 |
-
|
| 76 |
-
**Community Impact**: Use of inappropriate language or other behavior deemed
|
| 77 |
-
unprofessional or unwelcome in the community.
|
| 78 |
-
|
| 79 |
-
**Consequence**: A private, written warning from community leaders, providing
|
| 80 |
-
clarity around the nature of the violation and an explanation of why the
|
| 81 |
-
behavior was inappropriate. A public apology may be requested.
|
| 82 |
-
|
| 83 |
-
### 2. Warning
|
| 84 |
-
|
| 85 |
-
**Community Impact**: A violation through a single incident or series
|
| 86 |
-
of actions.
|
| 87 |
-
|
| 88 |
-
**Consequence**: A warning with consequences for continued behavior. No
|
| 89 |
-
interaction with the people involved, including unsolicited interaction with
|
| 90 |
-
those enforcing the Code of Conduct, for a specified period of time. This
|
| 91 |
-
includes avoiding interactions in community spaces as well as external channels
|
| 92 |
-
like social media. Violating these terms may lead to a temporary or
|
| 93 |
-
permanent ban.
|
| 94 |
-
|
| 95 |
-
### 3. Temporary Ban
|
| 96 |
-
|
| 97 |
-
**Community Impact**: A serious violation of community standards, including
|
| 98 |
-
sustained inappropriate behavior.
|
| 99 |
-
|
| 100 |
-
**Consequence**: A temporary ban from any sort of interaction or public
|
| 101 |
-
communication with the community for a specified period of time. No public or
|
| 102 |
-
private interaction with the people involved, including unsolicited interaction
|
| 103 |
-
with those enforcing the Code of Conduct, is allowed during this period.
|
| 104 |
-
Violating these terms may lead to a permanent ban.
|
| 105 |
-
|
| 106 |
-
### 4. Permanent Ban
|
| 107 |
-
|
| 108 |
-
**Community Impact**: Demonstrating a pattern of violation of community
|
| 109 |
-
standards, including sustained inappropriate behavior, harassment of an
|
| 110 |
-
individual, or aggression toward or disparagement of classes of individuals.
|
| 111 |
-
|
| 112 |
-
**Consequence**: A permanent ban from any sort of public interaction within
|
| 113 |
-
the community.
|
| 114 |
-
|
| 115 |
-
## Attribution
|
| 116 |
-
|
| 117 |
-
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
| 118 |
-
version 2.0, available at
|
| 119 |
-
https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
|
| 120 |
-
|
| 121 |
-
Community Impact Guidelines were inspired by [Mozilla's code of conduct
|
| 122 |
-
enforcement ladder](https://github.com/mozilla/diversity).
|
| 123 |
-
|
| 124 |
-
[homepage]: https://www.contributor-covenant.org
|
| 125 |
-
|
| 126 |
-
For answers to common questions about this code of conduct, see the FAQ at
|
| 127 |
-
https://www.contributor-covenant.org/faq. Translations are available at
|
| 128 |
-
https://www.contributor-covenant.org/translations.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
CHANGED
|
@@ -43,7 +43,7 @@ For example, consider an assistant working with customer records: MCP carries th
|
|
| 43 |
1. **Try the backend:** use the health request below to inspect this Space. It is the registry service, not a general-purpose agent or the calculator example.
|
| 44 |
2. **Build a server:** install the matching fork packages, define your tools, and configure `SecurityConfig` for the controls your application needs.
|
| 45 |
3. **Connect a client:** point an MCP client at your server’s endpoint. The [server-and-client quickstart](https://github.com/PureCipher/xsecuremcp2.0#build-an-mcp-server) demonstrates a tool call and receipt verification.
|
| 46 |
-
4. **Check enforcement:**
|
| 47 |
5. **Share and operate:** use PureCipher Publisher to submit projects to your chosen registry, and the separate xregistry console to manage it. Configure authentication, moderation, and persistent storage for your deployment.
|
| 48 |
|
| 49 |
## What this Space runs
|
|
@@ -96,8 +96,8 @@ The container runs as user 1000 and listens on port 8000. It installs the tested
|
|
| 96 |
|
| 97 |
| Field | Value |
|
| 98 |
| --- | --- |
|
| 99 |
-
| GitHub source | [`
|
| 100 |
-
| Package version | `0.0.1.
|
| 101 |
| Build metadata | [`build.json`](https://huggingface.co/spaces/purecipher/xsecuremcp/blob/main/build.json) |
|
| 102 |
|
| 103 |
Pushes to the GitHub repository’s `main` branch trigger tests, static checks, clean wheel installation checks, and Docker health checks before publication. Successful builds update this Space and replace its current wheel files. Hub history is retained.
|
|
|
|
| 43 |
1. **Try the backend:** use the health request below to inspect this Space. It is the registry service, not a general-purpose agent or the calculator example.
|
| 44 |
2. **Build a server:** install the matching fork packages, define your tools, and configure `SecurityConfig` for the controls your application needs.
|
| 45 |
3. **Connect a client:** point an MCP client at your server’s endpoint. The [server-and-client quickstart](https://github.com/PureCipher/xsecuremcp2.0#build-an-mcp-server) demonstrates a tool call and receipt verification.
|
| 46 |
+
4. **Check enforcement:** allow one operation, deny another, and inspect the resulting evidence. See the [project README](https://github.com/PureCipher/xsecuremcp2.0#readme) for the security configuration and its boundaries.
|
| 47 |
5. **Share and operate:** use PureCipher Publisher to submit projects to your chosen registry, and the separate xregistry console to manage it. Configure authentication, moderation, and persistent storage for your deployment.
|
| 48 |
|
| 49 |
## What this Space runs
|
|
|
|
| 96 |
|
| 97 |
| Field | Value |
|
| 98 |
| --- | --- |
|
| 99 |
+
| GitHub source | [`5bd407c3b781`](https://github.com/PureCipher/xsecuremcp2.0/commit/5bd407c3b7812ee3596ef0e1eea9afa5ecff0534) |
|
| 100 |
+
| Package version | `0.0.1.dev4090+5bd407c3` |
|
| 101 |
| Build metadata | [`build.json`](https://huggingface.co/spaces/purecipher/xsecuremcp/blob/main/build.json) |
|
| 102 |
|
| 103 |
Pushes to the GitHub repository’s `main` branch trigger tests, static checks, clean wheel installation checks, and Docker health checks before publication. Successful builds update this Space and replace its current wheel files. Hub history is retained.
|
README_OPENAPI.md
DELETED
|
@@ -1,246 +0,0 @@
|
|
| 1 |
-
# FastMCP OpenAPI Integration
|
| 2 |
-
|
| 3 |
-
This document explains how FastMCP's OpenAPI integration works, what features are supported, and how to extend it. The OpenAPI functionality is split across two main files:
|
| 4 |
-
|
| 5 |
-
- `server/openapi.py` - High-level FastMCP server implementation and MCP component creation
|
| 6 |
-
- `utilities/openapi.py` - Low-level OpenAPI parsing and intermediate representation
|
| 7 |
-
|
| 8 |
-
## Architecture Overview
|
| 9 |
-
|
| 10 |
-
```
|
| 11 |
-
OpenAPI Spec → Parse → HTTPRoute IR → Create MCP Components → FastMCP Server
|
| 12 |
-
```
|
| 13 |
-
|
| 14 |
-
### 1. Parsing Phase (`utilities/openapi.py`)
|
| 15 |
-
|
| 16 |
-
OpenAPI specifications are parsed into an intermediate representation (IR) that normalizes differences between OpenAPI 3.0 and 3.1:
|
| 17 |
-
|
| 18 |
-
- **Input**: Raw OpenAPI spec (dict)
|
| 19 |
-
- **Output**: List of `HTTPRoute` objects with normalized parameter information
|
| 20 |
-
- **Key Classes**:
|
| 21 |
-
- `HTTPRoute` - Represents a single operation
|
| 22 |
-
- `ParameterInfo` - Represents a parameter with location, style, explode, etc.
|
| 23 |
-
- `RequestBodyInfo` - Represents request body information
|
| 24 |
-
- `ResponseInfo` - Represents response information
|
| 25 |
-
|
| 26 |
-
### 2. Component Creation Phase (`server/openapi.py`)
|
| 27 |
-
|
| 28 |
-
HTTPRoute objects are converted into FastMCP components based on route mapping rules:
|
| 29 |
-
|
| 30 |
-
- **Tools** (`OpenAPITool`) - HTTP operations that can be called
|
| 31 |
-
- **Resources** (`OpenAPIResource`) - HTTP endpoints that return data
|
| 32 |
-
- **Resource Templates** (`OpenAPIResourceTemplate`) - Parameterized resources
|
| 33 |
-
|
| 34 |
-
## Parameter Handling
|
| 35 |
-
|
| 36 |
-
FastMCP supports various OpenAPI parameter serialization styles and formats:
|
| 37 |
-
|
| 38 |
-
### Supported Parameter Locations
|
| 39 |
-
- `query` - Query string parameters
|
| 40 |
-
- `path` - Path parameters
|
| 41 |
-
- `header` - HTTP headers
|
| 42 |
-
- `cookie` - Cookie parameters (parsed but not used in requests)
|
| 43 |
-
|
| 44 |
-
### Supported Parameter Styles
|
| 45 |
-
|
| 46 |
-
#### Query Parameters
|
| 47 |
-
- **`form`** (default) - Standard query parameter format
|
| 48 |
-
- `explode=true` (default): `?tags=red&tags=blue`
|
| 49 |
-
- `explode=false`: `?tags=red,blue`
|
| 50 |
-
- **`deepObject`** - Object parameters with bracket notation
|
| 51 |
-
- `explode=true`: `?filter[name]=John&filter[age]=30`
|
| 52 |
-
- `explode=false`: Falls back to JSON string (non-standard, logs warning)
|
| 53 |
-
|
| 54 |
-
#### Path Parameters
|
| 55 |
-
- **`simple`** (default) - Comma-separated for arrays: `/users/1,2,3`
|
| 56 |
-
|
| 57 |
-
#### Header Parameters
|
| 58 |
-
- **`simple`** (default) - Standard header format
|
| 59 |
-
|
| 60 |
-
### Parameter Type Support
|
| 61 |
-
|
| 62 |
-
#### Arrays
|
| 63 |
-
- String arrays with `explode=true/false`
|
| 64 |
-
- Number arrays with `explode=true/false`
|
| 65 |
-
- Boolean arrays with `explode=true/false`
|
| 66 |
-
- Complex object arrays (basic support, may not handle all cases)
|
| 67 |
-
|
| 68 |
-
#### Objects
|
| 69 |
-
- Objects with `deepObject` style and `explode=true`
|
| 70 |
-
- Objects with other styles fall back to JSON serialization
|
| 71 |
-
|
| 72 |
-
#### Primitives
|
| 73 |
-
- Strings, numbers, booleans
|
| 74 |
-
- Enums
|
| 75 |
-
- Default values
|
| 76 |
-
|
| 77 |
-
## Request Body Handling
|
| 78 |
-
|
| 79 |
-
### Supported Content Types
|
| 80 |
-
- `application/json` - JSON request bodies
|
| 81 |
-
|
| 82 |
-
### Schema Support
|
| 83 |
-
- Object schemas with properties
|
| 84 |
-
- Array schemas
|
| 85 |
-
- Primitive schemas
|
| 86 |
-
- Schema references (`$ref` to local schemas only)
|
| 87 |
-
- Required properties
|
| 88 |
-
- Default values
|
| 89 |
-
|
| 90 |
-
## Response Handling
|
| 91 |
-
|
| 92 |
-
### Content Type Detection
|
| 93 |
-
- `application/json` - Parsed as JSON
|
| 94 |
-
- `text/*` - Returned as text
|
| 95 |
-
- `application/xml` - Returned as text
|
| 96 |
-
- Other types - Returned as binary
|
| 97 |
-
|
| 98 |
-
### Output Schema Generation
|
| 99 |
-
- Success response schemas (200, 201, 202, 204)
|
| 100 |
-
- Object response wrapping for MCP compliance
|
| 101 |
-
- Schema compression (removes unused `$defs`)
|
| 102 |
-
|
| 103 |
-
## Route Mapping
|
| 104 |
-
|
| 105 |
-
Routes are mapped to MCP component types using `RouteMap` configurations:
|
| 106 |
-
|
| 107 |
-
```python
|
| 108 |
-
RouteMap(
|
| 109 |
-
methods=["GET", "POST"], # HTTP methods to match
|
| 110 |
-
pattern=r"/api/users/.*", # Regex pattern for path
|
| 111 |
-
mcp_type=MCPType.RESOURCE_TEMPLATE, # Target component type
|
| 112 |
-
tags={"user"}, # OpenAPI tags to match (AND condition)
|
| 113 |
-
mcp_tags={"fastmcp-user"} # Tags to add to created components
|
| 114 |
-
)
|
| 115 |
-
```
|
| 116 |
-
|
| 117 |
-
### Default Behavior
|
| 118 |
-
- All routes become **Tools** by default
|
| 119 |
-
- Use route maps to override specific patterns
|
| 120 |
-
|
| 121 |
-
### Component Types
|
| 122 |
-
- `MCPType.TOOL` - Callable operations
|
| 123 |
-
- `MCPType.RESOURCE` - Static data endpoints
|
| 124 |
-
- `MCPType.RESOURCE_TEMPLATE` - Parameterized data endpoints
|
| 125 |
-
- `MCPType.EXCLUDE` - Skip route entirely
|
| 126 |
-
|
| 127 |
-
## Known Limitations & Edge Cases
|
| 128 |
-
|
| 129 |
-
### Parameter Edge Cases
|
| 130 |
-
1. **Parameter Name Collisions** - When path/query parameters have same names as request body properties, non-body parameters get `__location` suffixes
|
| 131 |
-
2. **Complex Array Serialization** - Limited support for arrays containing objects
|
| 132 |
-
3. **Cookie Parameters** - Parsed but not used in requests
|
| 133 |
-
4. **Non-standard Combinations** - e.g., `deepObject` with `explode=false`
|
| 134 |
-
|
| 135 |
-
### Request Body Edge Cases
|
| 136 |
-
1. **Content Type Priority** - Only first available content type is used
|
| 137 |
-
2. **Nested Objects** - Deep nesting may not serialize correctly
|
| 138 |
-
3. **Binary Content** - No support for file uploads or binary data
|
| 139 |
-
|
| 140 |
-
### Response Edge Cases
|
| 141 |
-
1. **Multiple Content Types** - Only JSON-compatible types are used for output schemas
|
| 142 |
-
2. **Error Responses** - Not used for MCP output schema generation
|
| 143 |
-
3. **Response Headers** - Not captured or exposed
|
| 144 |
-
|
| 145 |
-
### Schema Edge Cases
|
| 146 |
-
1. **External References** - `$ref` to external files not supported
|
| 147 |
-
2. **Circular References** - May cause issues in schema processing
|
| 148 |
-
3. **Polymorphism** - `oneOf`/`anyOf`/`allOf` limited support
|
| 149 |
-
|
| 150 |
-
## Debugging Tips
|
| 151 |
-
|
| 152 |
-
### Common Issues
|
| 153 |
-
1. **"Unknown tool/resource"** - Check route mapping configuration
|
| 154 |
-
2. **Parameter not found** - Check for name collisions or incorrect style/explode
|
| 155 |
-
3. **Invalid request format** - Check parameter serialization and content types
|
| 156 |
-
4. **Schema validation errors** - Check for external refs or complex schemas
|
| 157 |
-
|
| 158 |
-
### Debugging Tools
|
| 159 |
-
```python
|
| 160 |
-
# Parse routes to inspect intermediate representation
|
| 161 |
-
routes = parse_openapi_to_http_routes(openapi_spec)
|
| 162 |
-
for route in routes:
|
| 163 |
-
print(f"{route.method} {route.path}")
|
| 164 |
-
for param in route.parameters:
|
| 165 |
-
print(f" {param.name} ({param.location}): style={param.style}, explode={param.explode}")
|
| 166 |
-
|
| 167 |
-
# Check component creation
|
| 168 |
-
server = FastMCP.from_openapi(openapi_spec, client)
|
| 169 |
-
tools = await server.get_tools()
|
| 170 |
-
print(f"Created {len(tools)} tools: {list(tools.keys())}")
|
| 171 |
-
```
|
| 172 |
-
|
| 173 |
-
### Logging
|
| 174 |
-
- Set `FASTMCP_LOG_LEVEL=DEBUG` to see detailed parameter processing
|
| 175 |
-
- Look for warnings about non-standard parameter combinations
|
| 176 |
-
- Check for schema parsing errors in logs
|
| 177 |
-
|
| 178 |
-
## Extension Points
|
| 179 |
-
|
| 180 |
-
### Adding New Parameter Styles
|
| 181 |
-
1. Add style handling in `utilities/openapi.py` - `ParameterInfo` class
|
| 182 |
-
2. Implement serialization logic in `server/openapi.py` - `OpenAPITool.run()`
|
| 183 |
-
3. Add tests for parsing and serialization
|
| 184 |
-
|
| 185 |
-
### Adding New Content Types
|
| 186 |
-
1. Extend request body handling in `OpenAPITool.run()`
|
| 187 |
-
2. Add response parsing logic for new types
|
| 188 |
-
3. Update content type priority in utilities
|
| 189 |
-
|
| 190 |
-
### Custom Route Mapping
|
| 191 |
-
Use `route_map_fn` for complex routing logic:
|
| 192 |
-
|
| 193 |
-
```python
|
| 194 |
-
def custom_mapper(route: HTTPRoute, current_type: MCPType) -> MCPType:
|
| 195 |
-
if route.path.startswith("/admin"):
|
| 196 |
-
return MCPType.EXCLUDE
|
| 197 |
-
return current_type
|
| 198 |
-
|
| 199 |
-
server = FastMCP.from_openapi(spec, client, route_map_fn=custom_mapper)
|
| 200 |
-
```
|
| 201 |
-
|
| 202 |
-
## Testing Patterns
|
| 203 |
-
|
| 204 |
-
### Unit Tests
|
| 205 |
-
- Test parameter parsing with various styles/explode combinations
|
| 206 |
-
- Test route mapping with different patterns and tags
|
| 207 |
-
- Test schema generation and compression
|
| 208 |
-
|
| 209 |
-
### Integration Tests
|
| 210 |
-
- Mock HTTP client to verify actual request parameters
|
| 211 |
-
- Test end-to-end component creation and execution
|
| 212 |
-
- Test error handling and edge cases
|
| 213 |
-
|
| 214 |
-
### Example Test Pattern
|
| 215 |
-
```python
|
| 216 |
-
async def test_parameter_style():
|
| 217 |
-
# 1. Create OpenAPI spec with specific parameter configuration
|
| 218 |
-
spec = {"openapi": "3.1.0", ...}
|
| 219 |
-
|
| 220 |
-
# 2. Parse and create components
|
| 221 |
-
routes = parse_openapi_to_http_routes(spec)
|
| 222 |
-
tool = OpenAPITool(mock_client, routes[0], ...)
|
| 223 |
-
|
| 224 |
-
# 3. Execute and verify request parameters
|
| 225 |
-
await tool.run({"param": "value"})
|
| 226 |
-
actual_params = mock_client.request.call_args.kwargs["params"]
|
| 227 |
-
assert actual_params == expected_params
|
| 228 |
-
```
|
| 229 |
-
|
| 230 |
-
## Testing
|
| 231 |
-
|
| 232 |
-
OpenAPI functionality is tested across multiple files in `tests/server/openapi/`:
|
| 233 |
-
|
| 234 |
-
- `test_basic_functionality.py` - Core component creation and execution
|
| 235 |
-
- `test_explode_integration.py` - Parameter explode behavior
|
| 236 |
-
- `test_deepobject_style.py` - DeepObject style parameter encoding
|
| 237 |
-
- `test_parameter_collisions.py` - Parameter name collision handling
|
| 238 |
-
- `test_openapi_path_parameters.py` - Path parameter serialization
|
| 239 |
-
- `test_configuration.py` - Route mapping and MCP names
|
| 240 |
-
- `test_description_propagation.py` - Schema and description handling
|
| 241 |
-
|
| 242 |
-
When adding new OpenAPI features, create focused test files rather than adding to existing monolithic files.
|
| 243 |
-
|
| 244 |
-
---
|
| 245 |
-
|
| 246 |
-
*This document should be updated when new OpenAPI features are added or when edge cases are discovered and addressed.*
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Windows_Notes.md
DELETED
|
@@ -1,58 +0,0 @@
|
|
| 1 |
-
# Getting your development environment set up properly
|
| 2 |
-
To get your environment up and running properly, you'll need a slightly different set of commands that are windows specific:
|
| 3 |
-
```bash
|
| 4 |
-
uv venv
|
| 5 |
-
.venv\Scripts\activate
|
| 6 |
-
uv pip install -e ".[dev]"
|
| 7 |
-
```
|
| 8 |
-
|
| 9 |
-
This will install the package in editable mode, and install the development dependencies.
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
# Fixing `AttributeError: module 'collections' has no attribute 'Callable'`
|
| 13 |
-
- open `.venv\Lib\site-packages\pyreadline\py3k_compat.py`
|
| 14 |
-
- change `return isinstance(x, collections.Callable)` to
|
| 15 |
-
```
|
| 16 |
-
from collections.abc import Callable
|
| 17 |
-
return isinstance(x, Callable)
|
| 18 |
-
```
|
| 19 |
-
|
| 20 |
-
# Helpful notes
|
| 21 |
-
For developing FastMCP
|
| 22 |
-
## Install local development version of FastMCP into a local FastMCP project server
|
| 23 |
-
- ensure
|
| 24 |
-
- change directories to your FastMCP Server location so you can install it in your .venv
|
| 25 |
-
- run `.venv\Scripts\activate` to activate your virtual environment
|
| 26 |
-
- Then run a series of commands to uninstall the old version and install the new
|
| 27 |
-
```bash
|
| 28 |
-
# First uninstall
|
| 29 |
-
uv pip uninstall fastmcp
|
| 30 |
-
|
| 31 |
-
# Clean any build artifacts in your fastmcp directory
|
| 32 |
-
cd C:\path\to\fastmcp
|
| 33 |
-
del /s /q *.egg-info
|
| 34 |
-
|
| 35 |
-
# Then reinstall in your weather project
|
| 36 |
-
cd C:\path\to\new\fastmcp_server
|
| 37 |
-
uv pip install --no-cache-dir -e C:\Users\justj\PycharmProjects\fastmcp
|
| 38 |
-
|
| 39 |
-
# Check that it installed properly and has the correct git hash
|
| 40 |
-
pip show fastmcp
|
| 41 |
-
```
|
| 42 |
-
|
| 43 |
-
## Running the FastMCP server with Inspector
|
| 44 |
-
MCP comes with a node.js application called Inspector that can be used to inspect the FastMCP server. To run the inspector, you'll need to install node.js and npm. Then you can run the following commands:
|
| 45 |
-
```bash
|
| 46 |
-
fastmcp dev server.py
|
| 47 |
-
```
|
| 48 |
-
This will launch a web app on http://localhost:5173/ that you can use to inspect the FastMCP server.
|
| 49 |
-
|
| 50 |
-
## If you start development before creating a fork - your get out of jail free card
|
| 51 |
-
- Add your fork as a new remote to your local repository `git remote add fork git@github.com:YOUR-USERNAME/REPOSITORY-NAME.git`
|
| 52 |
-
- This will add your repo, short named 'fork', as a remote to your local repository
|
| 53 |
-
- Verify that it was added correctly by running `git remote -v`
|
| 54 |
-
- Commit your changes
|
| 55 |
-
- Push your changes to your fork `git push fork <branch>`
|
| 56 |
-
- Create your pull request on GitHub
|
| 57 |
-
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
build.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"repository": "PureCipher/xsecuremcp2.0",
|
| 3 |
-
"commit": "
|
| 4 |
-
"version": "0.0.1.
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"repository": "PureCipher/xsecuremcp2.0",
|
| 3 |
+
"commit": "5bd407c3b7812ee3596ef0e1eea9afa5ecff0534",
|
| 4 |
+
"version": "0.0.1.dev4090+5bd407c3"
|
| 5 |
}
|
docs/.cursor/rules/mintlify.mdc
DELETED
|
@@ -1,364 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
description:
|
| 3 |
-
globs: *.mdx
|
| 4 |
-
alwaysApply: false
|
| 5 |
-
---
|
| 6 |
-
# Mintlify technical writing assistant
|
| 7 |
-
|
| 8 |
-
You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.
|
| 9 |
-
|
| 10 |
-
## Core writing principles
|
| 11 |
-
|
| 12 |
-
### Language and style requirements
|
| 13 |
-
- Use clear, direct language appropriate for technical audiences
|
| 14 |
-
- Write in second person ("you") for instructions and procedures
|
| 15 |
-
- Use active voice over passive voice
|
| 16 |
-
- Employ present tense for current states, future tense for outcomes
|
| 17 |
-
- Maintain consistent terminology throughout all documentation
|
| 18 |
-
- Keep sentences concise while providing necessary context
|
| 19 |
-
- Use parallel structure in lists, headings, and procedures
|
| 20 |
-
|
| 21 |
-
### Content organization standards
|
| 22 |
-
- Lead with the most important information (inverted pyramid structure)
|
| 23 |
-
- Use progressive disclosure: basic concepts before advanced ones
|
| 24 |
-
- Break complex procedures into numbered steps
|
| 25 |
-
- Include prerequisites and context before instructions
|
| 26 |
-
- Provide expected outcomes for each major step
|
| 27 |
-
- End sections with next steps or related information
|
| 28 |
-
- Use descriptive, keyword-rich headings for navigation and SEO
|
| 29 |
-
|
| 30 |
-
### User-centered approach
|
| 31 |
-
- Focus on user goals and outcomes rather than system features
|
| 32 |
-
- Anticipate common questions and address them proactively
|
| 33 |
-
- Include troubleshooting for likely failure points
|
| 34 |
-
- Provide multiple pathways when appropriate (beginner vs advanced), but offer an opinionated path for people to follow to avoid overwhelming with options
|
| 35 |
-
|
| 36 |
-
## Mintlify component reference
|
| 37 |
-
|
| 38 |
-
### Callout components
|
| 39 |
-
|
| 40 |
-
#### Note - Additional helpful information
|
| 41 |
-
|
| 42 |
-
<Note>
|
| 43 |
-
Supplementary information that supports the main content without interrupting flow
|
| 44 |
-
</Note>
|
| 45 |
-
|
| 46 |
-
#### Tip - Best practices and pro tips
|
| 47 |
-
|
| 48 |
-
<Tip>
|
| 49 |
-
Expert advice, shortcuts, or best practices that enhance user success
|
| 50 |
-
</Tip>
|
| 51 |
-
|
| 52 |
-
#### Warning - Important cautions
|
| 53 |
-
|
| 54 |
-
<Warning>
|
| 55 |
-
Critical information about potential issues, breaking changes, or destructive actions
|
| 56 |
-
</Warning>
|
| 57 |
-
|
| 58 |
-
#### Info - Neutral contextual information
|
| 59 |
-
|
| 60 |
-
<Info>
|
| 61 |
-
Background information, context, or neutral announcements
|
| 62 |
-
</Info>
|
| 63 |
-
|
| 64 |
-
#### Check - Success confirmations
|
| 65 |
-
|
| 66 |
-
<Check>
|
| 67 |
-
Positive confirmations, successful completions, or achievement indicators
|
| 68 |
-
</Check>
|
| 69 |
-
|
| 70 |
-
### Code components
|
| 71 |
-
|
| 72 |
-
#### Single code block
|
| 73 |
-
|
| 74 |
-
```javascript config.js
|
| 75 |
-
const apiConfig = {
|
| 76 |
-
baseURL: 'https://api.example.com',
|
| 77 |
-
timeout: 5000,
|
| 78 |
-
headers: {
|
| 79 |
-
'Authorization': `Bearer ${process.env.API_TOKEN}`
|
| 80 |
-
}
|
| 81 |
-
};
|
| 82 |
-
```
|
| 83 |
-
|
| 84 |
-
#### Code group with multiple languages
|
| 85 |
-
|
| 86 |
-
<CodeGroup>
|
| 87 |
-
```javascript Node.js
|
| 88 |
-
const response = await fetch('/api/endpoint', {
|
| 89 |
-
headers: { Authorization: `Bearer ${apiKey}` }
|
| 90 |
-
});
|
| 91 |
-
```
|
| 92 |
-
|
| 93 |
-
```python Python
|
| 94 |
-
import requests
|
| 95 |
-
response = requests.get('/api/endpoint',
|
| 96 |
-
headers={'Authorization': f'Bearer {api_key}'})
|
| 97 |
-
```
|
| 98 |
-
|
| 99 |
-
```curl cURL
|
| 100 |
-
curl -X GET '/api/endpoint' \
|
| 101 |
-
-H 'Authorization: Bearer YOUR_API_KEY'
|
| 102 |
-
```
|
| 103 |
-
</CodeGroup>
|
| 104 |
-
|
| 105 |
-
#### Request/Response examples
|
| 106 |
-
|
| 107 |
-
<RequestExample>
|
| 108 |
-
```bash cURL
|
| 109 |
-
curl -X POST 'https://api.example.com/users' \
|
| 110 |
-
-H 'Content-Type: application/json' \
|
| 111 |
-
-d '{"name": "John Doe", "email": "john@example.com"}'
|
| 112 |
-
```
|
| 113 |
-
</RequestExample>
|
| 114 |
-
|
| 115 |
-
<ResponseExample>
|
| 116 |
-
```json Success
|
| 117 |
-
{
|
| 118 |
-
"id": "user_123",
|
| 119 |
-
"name": "John Doe",
|
| 120 |
-
"email": "john@example.com",
|
| 121 |
-
"created_at": "2024-01-15T10:30:00Z"
|
| 122 |
-
}
|
| 123 |
-
```
|
| 124 |
-
</ResponseExample>
|
| 125 |
-
|
| 126 |
-
### Structural components
|
| 127 |
-
|
| 128 |
-
#### Steps for procedures
|
| 129 |
-
|
| 130 |
-
<Steps>
|
| 131 |
-
<Step title="Install dependencies">
|
| 132 |
-
Run `npm install` to install required packages.
|
| 133 |
-
|
| 134 |
-
<Check>
|
| 135 |
-
Verify installation by running `npm list`.
|
| 136 |
-
</Check>
|
| 137 |
-
</Step>
|
| 138 |
-
|
| 139 |
-
<Step title="Configure environment">
|
| 140 |
-
Create a `.env` file with your API credentials.
|
| 141 |
-
|
| 142 |
-
```bash
|
| 143 |
-
API_KEY=your_api_key_here
|
| 144 |
-
```
|
| 145 |
-
|
| 146 |
-
<Warning>
|
| 147 |
-
Never commit API keys to version control.
|
| 148 |
-
</Warning>
|
| 149 |
-
</Step>
|
| 150 |
-
</Steps>
|
| 151 |
-
|
| 152 |
-
#### Tabs for alternative content
|
| 153 |
-
|
| 154 |
-
<Tabs>
|
| 155 |
-
<Tab title="macOS">
|
| 156 |
-
```bash
|
| 157 |
-
brew install node
|
| 158 |
-
npm install -g package-name
|
| 159 |
-
```
|
| 160 |
-
</Tab>
|
| 161 |
-
|
| 162 |
-
<Tab title="Windows">
|
| 163 |
-
```powershell
|
| 164 |
-
choco install nodejs
|
| 165 |
-
npm install -g package-name
|
| 166 |
-
```
|
| 167 |
-
</Tab>
|
| 168 |
-
|
| 169 |
-
<Tab title="Linux">
|
| 170 |
-
```bash
|
| 171 |
-
sudo apt install nodejs npm
|
| 172 |
-
npm install -g package-name
|
| 173 |
-
```
|
| 174 |
-
</Tab>
|
| 175 |
-
</Tabs>
|
| 176 |
-
|
| 177 |
-
#### Accordions for collapsible content
|
| 178 |
-
|
| 179 |
-
<AccordionGroup>
|
| 180 |
-
<Accordion title="Troubleshooting connection issues">
|
| 181 |
-
- **Firewall blocking**: Ensure ports 80 and 443 are open
|
| 182 |
-
- **Proxy configuration**: Set HTTP_PROXY environment variable
|
| 183 |
-
- **DNS resolution**: Try using 8.8.8.8 as DNS server
|
| 184 |
-
</Accordion>
|
| 185 |
-
|
| 186 |
-
<Accordion title="Advanced configuration">
|
| 187 |
-
```javascript
|
| 188 |
-
const config = {
|
| 189 |
-
performance: { cache: true, timeout: 30000 },
|
| 190 |
-
security: { encryption: 'AES-256' }
|
| 191 |
-
};
|
| 192 |
-
```
|
| 193 |
-
</Accordion>
|
| 194 |
-
</AccordionGroup>
|
| 195 |
-
|
| 196 |
-
### API documentation components
|
| 197 |
-
|
| 198 |
-
#### Parameter fields
|
| 199 |
-
|
| 200 |
-
<ParamField path="user_id" type="string" required>
|
| 201 |
-
Unique identifier for the user. Must be a valid UUID v4 format.
|
| 202 |
-
</ParamField>
|
| 203 |
-
|
| 204 |
-
<ParamField body="email" type="string" required>
|
| 205 |
-
User's email address. Must be valid and unique within the system.
|
| 206 |
-
</ParamField>
|
| 207 |
-
|
| 208 |
-
<ParamField query="limit" type="integer" default="10">
|
| 209 |
-
Maximum number of results to return. Range: 1-100.
|
| 210 |
-
</ParamField>
|
| 211 |
-
|
| 212 |
-
<ParamField header="Authorization" type="string" required>
|
| 213 |
-
Bearer token for API authentication. Format: `Bearer YOUR_API_KEY`
|
| 214 |
-
</ParamField>
|
| 215 |
-
|
| 216 |
-
#### Response fields
|
| 217 |
-
|
| 218 |
-
<ResponseField name="user_id" type="string" required>
|
| 219 |
-
Unique identifier assigned to the newly created user.
|
| 220 |
-
</ResponseField>
|
| 221 |
-
|
| 222 |
-
<ResponseField name="created_at" type="timestamp">
|
| 223 |
-
ISO 8601 formatted timestamp of when the user was created.
|
| 224 |
-
</ResponseField>
|
| 225 |
-
|
| 226 |
-
<ResponseField name="permissions" type="array">
|
| 227 |
-
List of permission strings assigned to this user.
|
| 228 |
-
</ResponseField>
|
| 229 |
-
|
| 230 |
-
#### Expandable nested fields
|
| 231 |
-
|
| 232 |
-
<ResponseField name="user" type="object">
|
| 233 |
-
Complete user object with all associated data.
|
| 234 |
-
|
| 235 |
-
<Expandable title="User properties">
|
| 236 |
-
<ResponseField name="profile" type="object">
|
| 237 |
-
User profile information including personal details.
|
| 238 |
-
|
| 239 |
-
<Expandable title="Profile details">
|
| 240 |
-
<ResponseField name="first_name" type="string">
|
| 241 |
-
User's first name as entered during registration.
|
| 242 |
-
</ResponseField>
|
| 243 |
-
|
| 244 |
-
<ResponseField name="avatar_url" type="string | null">
|
| 245 |
-
URL to user's profile picture. Returns null if no avatar is set.
|
| 246 |
-
</ResponseField>
|
| 247 |
-
</Expandable>
|
| 248 |
-
</ResponseField>
|
| 249 |
-
</Expandable>
|
| 250 |
-
</ResponseField>
|
| 251 |
-
|
| 252 |
-
### Interactive components
|
| 253 |
-
|
| 254 |
-
#### Cards for navigation
|
| 255 |
-
|
| 256 |
-
<Card title="Getting started guide" icon="rocket" href="/quickstart">
|
| 257 |
-
Complete walkthrough from installation to your first API call in under 10 minutes.
|
| 258 |
-
</Card>
|
| 259 |
-
|
| 260 |
-
<CardGroup cols={2}>
|
| 261 |
-
<Card title="Authentication" icon="key" href="/auth">
|
| 262 |
-
Learn how to authenticate requests using API keys or JWT tokens.
|
| 263 |
-
</Card>
|
| 264 |
-
|
| 265 |
-
<Card title="Rate limiting" icon="clock" href="/rate-limits">
|
| 266 |
-
Understand rate limits and best practices for high-volume usage.
|
| 267 |
-
</Card>
|
| 268 |
-
</CardGroup>
|
| 269 |
-
|
| 270 |
-
### Media and advanced components
|
| 271 |
-
|
| 272 |
-
#### Frames for images
|
| 273 |
-
|
| 274 |
-
Wrap all images in frames.
|
| 275 |
-
|
| 276 |
-
<Frame>
|
| 277 |
-
<img src="/images/dashboard.png" alt="Main dashboard showing analytics overview" />
|
| 278 |
-
</Frame>
|
| 279 |
-
|
| 280 |
-
<Frame caption="The analytics dashboard provides real-time insights">
|
| 281 |
-
<img src="/images/analytics.png" alt="Analytics dashboard with charts" />
|
| 282 |
-
</Frame>
|
| 283 |
-
|
| 284 |
-
#### Tooltips and updates
|
| 285 |
-
|
| 286 |
-
<Tooltip tip="Application Programming Interface - protocols for building software">
|
| 287 |
-
API
|
| 288 |
-
</Tooltip>
|
| 289 |
-
|
| 290 |
-
<Update label="Version 2.1.0" description="Released March 15, 2024">
|
| 291 |
-
## New features
|
| 292 |
-
- Added bulk user import functionality
|
| 293 |
-
- Improved error messages with actionable suggestions
|
| 294 |
-
|
| 295 |
-
## Bug fixes
|
| 296 |
-
- Fixed pagination issue with large datasets
|
| 297 |
-
- Resolved authentication timeout problems
|
| 298 |
-
</Update>
|
| 299 |
-
|
| 300 |
-
## Required page structure
|
| 301 |
-
|
| 302 |
-
Every documentation page must begin with YAML frontmatter:
|
| 303 |
-
|
| 304 |
-
```yaml
|
| 305 |
-
---
|
| 306 |
-
title: "Clear, specific, keyword-rich title"
|
| 307 |
-
description: "Concise description explaining page purpose and value"
|
| 308 |
-
---
|
| 309 |
-
```
|
| 310 |
-
|
| 311 |
-
## Content quality standards
|
| 312 |
-
|
| 313 |
-
### Code examples requirements
|
| 314 |
-
- Always include complete, runnable examples that users can copy and execute
|
| 315 |
-
- Show proper error handling and edge case management
|
| 316 |
-
- Use realistic data instead of placeholder values
|
| 317 |
-
- Include expected outputs and results for verification
|
| 318 |
-
- Test all code examples thoroughly before publishing
|
| 319 |
-
- Specify language and include filename when relevant
|
| 320 |
-
- Add explanatory comments for complex logic
|
| 321 |
-
|
| 322 |
-
### API documentation requirements
|
| 323 |
-
- Document all parameters including optional ones with clear descriptions
|
| 324 |
-
- Show both success and error response examples with realistic data
|
| 325 |
-
- Include rate limiting information with specific limits
|
| 326 |
-
- Provide authentication examples showing proper format
|
| 327 |
-
- Explain all HTTP status codes and error handling
|
| 328 |
-
- Cover complete request/response cycles
|
| 329 |
-
|
| 330 |
-
### Accessibility requirements
|
| 331 |
-
- Include descriptive alt text for all images and diagrams
|
| 332 |
-
- Use specific, actionable link text instead of "click here"
|
| 333 |
-
- Ensure proper heading hierarchy starting with H2
|
| 334 |
-
- Provide keyboard navigation considerations
|
| 335 |
-
- Use sufficient color contrast in examples and visuals
|
| 336 |
-
- Structure content for easy scanning with headers and lists
|
| 337 |
-
|
| 338 |
-
## AI assistant instructions
|
| 339 |
-
|
| 340 |
-
### Component selection logic
|
| 341 |
-
- Use **Steps** for procedures, tutorials, setup guides, and sequential instructions
|
| 342 |
-
- Use **Tabs** for platform-specific content or alternative approaches
|
| 343 |
-
- Use **CodeGroup** when showing the same concept in multiple languages
|
| 344 |
-
- Use **Accordions** for supplementary information that might interrupt flow
|
| 345 |
-
- Use **Cards and CardGroup** for navigation, feature overviews, and related resources
|
| 346 |
-
- Use **RequestExample/ResponseExample** specifically for API endpoint documentation
|
| 347 |
-
- Use **ParamField** for API parameters, **ResponseField** for API responses
|
| 348 |
-
- Use **Expandable** for nested object properties or hierarchical information
|
| 349 |
-
|
| 350 |
-
### Quality assurance checklist
|
| 351 |
-
- Verify all code examples are syntactically correct and executable
|
| 352 |
-
- Test all links to ensure they are functional and lead to relevant content
|
| 353 |
-
- Validate Mintlify component syntax with all required properties
|
| 354 |
-
- Confirm proper heading hierarchy with H2 for main sections, H3 for subsections
|
| 355 |
-
- Ensure content flows logically from basic concepts to advanced topics
|
| 356 |
-
- Check for consistency in terminology, formatting, and component usage
|
| 357 |
-
|
| 358 |
-
### Error prevention strategies
|
| 359 |
-
- Always include realistic error handling in code examples
|
| 360 |
-
- Provide dedicated troubleshooting sections for complex procedures
|
| 361 |
-
- Explain prerequisites clearly before beginning instructions
|
| 362 |
-
- Include verification and testing steps with expected outcomes
|
| 363 |
-
- Add appropriate warnings for destructive or security-sensitive actions
|
| 364 |
-
- Validate all technical information through testing before publication
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
docs/REFLEXIVE_CORE_WHITEPAPER.md
DELETED
|
@@ -1,633 +0,0 @@
|
|
| 1 |
-
# Reflexive Core: A Self-Monitoring and Self-Correcting Runtime for Secure MCP
|
| 2 |
-
|
| 3 |
-
## Executive Summary
|
| 4 |
-
|
| 5 |
-
The Reflexive Core represents a paradigm shift in Model Context Protocol (MCP) security architecture, introducing autonomous self-monitoring and self-correcting capabilities that enable real-time threat detection, policy enforcement, and automated incident response. This whitepaper presents the technical architecture, implementation details, and security guarantees of a reflexive runtime system that continuously monitors MCP operations for anomalies, policy violations, and ledger inconsistencies while automatically taking corrective actions.
|
| 6 |
-
|
| 7 |
-
## Table of Contents
|
| 8 |
-
|
| 9 |
-
1. [Introduction](#introduction)
|
| 10 |
-
2. [Architecture Overview](#architecture-overview)
|
| 11 |
-
3. [Core Components](#core-components)
|
| 12 |
-
4. [Security Model](#security-model)
|
| 13 |
-
5. [Implementation Details](#implementation-details)
|
| 14 |
-
6. [Performance Characteristics](#performance-characteristics)
|
| 15 |
-
7. [Security Analysis](#security-analysis)
|
| 16 |
-
8. [Future Enhancements](#future-enhancements)
|
| 17 |
-
9. [Conclusion](#conclusion)
|
| 18 |
-
|
| 19 |
-
## Introduction
|
| 20 |
-
|
| 21 |
-
### Problem Statement
|
| 22 |
-
|
| 23 |
-
Traditional MCP implementations rely on static policy enforcement and manual intervention for security incident response. This reactive approach creates several critical vulnerabilities:
|
| 24 |
-
|
| 25 |
-
1. **Temporal Gaps**: Time between threat detection and response allows for exploitation
|
| 26 |
-
2. **Human Bottlenecks**: Manual intervention introduces delays and potential errors
|
| 27 |
-
3. **Incomplete Coverage**: Static policies cannot adapt to novel attack vectors
|
| 28 |
-
4. **Audit Complexity**: Manual correlation of events across distributed systems
|
| 29 |
-
5. **Compliance Gaps**: Inconsistent enforcement of regulatory requirements
|
| 30 |
-
|
| 31 |
-
### Solution Architecture
|
| 32 |
-
|
| 33 |
-
The Reflexive Core addresses these limitations through a multi-layered, event-driven architecture that provides:
|
| 34 |
-
|
| 35 |
-
- **Continuous Monitoring**: Real-time analysis of all MCP operations
|
| 36 |
-
- **Automated Response**: Immediate corrective actions without human intervention
|
| 37 |
-
- **Adaptive Policies**: Dynamic policy adjustment based on threat intelligence
|
| 38 |
-
- **Cryptographic Auditability**: Tamper-evident logging with proof chains
|
| 39 |
-
- **Self-Healing**: Automatic recovery from detected anomalies
|
| 40 |
-
|
| 41 |
-
## Architecture Overview
|
| 42 |
-
|
| 43 |
-
### System Design Principles
|
| 44 |
-
|
| 45 |
-
The Reflexive Core is built on four fundamental principles:
|
| 46 |
-
|
| 47 |
-
1. **Autonomy**: The system operates independently with minimal human oversight
|
| 48 |
-
2. **Transparency**: All decisions and actions are cryptographically verifiable
|
| 49 |
-
3. **Resilience**: The system continues operating even when components fail
|
| 50 |
-
4. **Extensibility**: New monitoring and response capabilities can be added dynamically
|
| 51 |
-
|
| 52 |
-
### High-Level Architecture
|
| 53 |
-
|
| 54 |
-
```
|
| 55 |
-
┌─────────────────────────────────────────────────────────────────┐
|
| 56 |
-
│ Reflexive Core Runtime │
|
| 57 |
-
├─────────────────────────────────────────────────────────────────┤
|
| 58 |
-
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
|
| 59 |
-
│ │ Policy │ │ Ledger │ │ Anomaly │ │
|
| 60 |
-
│ │ Monitor │ │ Monitor │ │ Detector │ │
|
| 61 |
-
│ └─────────────┘ └─────────────┘ └─────────────┘ │
|
| 62 |
-
│ │ │ │ │
|
| 63 |
-
│ └────────────────┼────────────────┘ │
|
| 64 |
-
│ │ │
|
| 65 |
-
│ ┌─────────────────────────────────────────────────────────┐ │
|
| 66 |
-
│ │ Reflexive Engine │ │
|
| 67 |
-
│ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │
|
| 68 |
-
│ │ │ Event │ │ Decision │ │ Action │ │ │
|
| 69 |
-
│ │ │ Processor │ │ Engine │ │ Executor │ │ │
|
| 70 |
-
│ │ └─────────────┘ └─────────────┘ └─────────────┘ │ │
|
| 71 |
-
│ └─────────────────────────────────────────────────────────┘ │
|
| 72 |
-
│ │ │
|
| 73 |
-
│ ┌────────────────────��────────────────────────────────────┐ │
|
| 74 |
-
│ │ Action Framework │ │
|
| 75 |
-
│ │ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │ │
|
| 76 |
-
│ │ │ Halt │ │Escalate │ │ Monitor │ │ Allow │ │ │
|
| 77 |
-
│ │ └─────────┘ └─────────┘ └─────────┘ └─────────┘ │ │
|
| 78 |
-
│ └─────────────────────────────────────────────────────────┘ │
|
| 79 |
-
└─────────────────────────────────────────────────────────────────┘
|
| 80 |
-
```
|
| 81 |
-
|
| 82 |
-
### Event Flow Architecture
|
| 83 |
-
|
| 84 |
-
The system processes events through a multi-stage pipeline:
|
| 85 |
-
|
| 86 |
-
1. **Event Ingestion**: Actions are submitted to the reflexive engine
|
| 87 |
-
2. **Parallel Monitoring**: Multiple monitors analyze the action simultaneously
|
| 88 |
-
3. **Risk Assessment**: The engine evaluates combined monitor outputs
|
| 89 |
-
4. **Decision Making**: Appropriate response actions are determined
|
| 90 |
-
5. **Action Execution**: Corrective actions are executed automatically
|
| 91 |
-
6. **Audit Logging**: All decisions and actions are cryptographically logged
|
| 92 |
-
|
| 93 |
-
## Core Components
|
| 94 |
-
|
| 95 |
-
### ReflexiveEngine
|
| 96 |
-
|
| 97 |
-
The `ReflexiveEngine` serves as the central orchestrator, implementing a sophisticated decision-making system based on multi-dimensional risk assessment.
|
| 98 |
-
|
| 99 |
-
#### Key Features
|
| 100 |
-
|
| 101 |
-
- **Asynchronous Event Processing**: Non-blocking event queue with configurable timeouts
|
| 102 |
-
- **Dynamic Monitor Registration**: Monitors can be added/removed at runtime
|
| 103 |
-
- **Risk-Based Decision Making**: Sophisticated risk assessment algorithm
|
| 104 |
-
- **Cryptographic Integrity**: All decisions include tamper-evident proof hashes
|
| 105 |
-
|
| 106 |
-
#### Risk Assessment Algorithm
|
| 107 |
-
|
| 108 |
-
The engine employs a multi-factor risk assessment model:
|
| 109 |
-
|
| 110 |
-
```python
|
| 111 |
-
def _assess_risk_level(self, violations: List[Dict], anomalies: List[Dict]) -> RiskLevel:
|
| 112 |
-
"""Multi-dimensional risk assessment algorithm."""
|
| 113 |
-
|
| 114 |
-
# Critical risk factors
|
| 115 |
-
critical_violations = [v for v in violations if v.get("severity") == "critical"]
|
| 116 |
-
critical_anomalies = [a for a in anomalies if a.get("severity") == "critical"]
|
| 117 |
-
if critical_violations or critical_anomalies:
|
| 118 |
-
return RiskLevel.CRITICAL
|
| 119 |
-
|
| 120 |
-
# High risk factors
|
| 121 |
-
high_violations = [v for v in violations if v.get("severity") == "high"]
|
| 122 |
-
high_anomalies = [a for a in anomalies if a.get("severity") == "high"]
|
| 123 |
-
total_issues = len(violations) + len(anomalies)
|
| 124 |
-
|
| 125 |
-
if high_violations or high_anomalies or total_issues >= 5:
|
| 126 |
-
return RiskLevel.HIGH
|
| 127 |
-
|
| 128 |
-
# Medium risk factors
|
| 129 |
-
medium_violations = [v for v in violations if v.get("severity") == "medium"]
|
| 130 |
-
medium_anomalies = [a for a in anomalies if a.get("severity") == "medium"]
|
| 131 |
-
|
| 132 |
-
if medium_violations or medium_anomalies or total_issues >= 2:
|
| 133 |
-
return RiskLevel.MEDIUM
|
| 134 |
-
|
| 135 |
-
return RiskLevel.LOW
|
| 136 |
-
```
|
| 137 |
-
|
| 138 |
-
#### Decision Matrix
|
| 139 |
-
|
| 140 |
-
The engine implements a sophisticated decision matrix that maps risk levels to appropriate actions:
|
| 141 |
-
|
| 142 |
-
| Risk Level | Primary Action | Secondary Action | Escalation Target |
|
| 143 |
-
|------------|----------------|------------------|-------------------|
|
| 144 |
-
| CRITICAL | HALT | ESCALATE | security_admin |
|
| 145 |
-
| HIGH | HALT | ESCALATE | system_admin |
|
| 146 |
-
| MEDIUM | ESCALATE | MONITOR | monitoring_team |
|
| 147 |
-
| LOW | MONITOR | ALLOW | - |
|
| 148 |
-
|
| 149 |
-
### Monitoring Components
|
| 150 |
-
|
| 151 |
-
#### PolicyMonitor
|
| 152 |
-
|
| 153 |
-
The `PolicyMonitor` implements real-time policy enforcement with sophisticated pattern recognition:
|
| 154 |
-
|
| 155 |
-
**Detection Capabilities:**
|
| 156 |
-
- **Administrative Access Violations**: Detects unauthorized privilege escalation attempts
|
| 157 |
-
- **Rate Limiting**: Identifies potential DoS attacks through frequency analysis
|
| 158 |
-
- **Resource Access Patterns**: Monitors access to sensitive resources
|
| 159 |
-
- **Session Anomalies**: Detects unusual session behavior patterns
|
| 160 |
-
|
| 161 |
-
**Implementation Highlights:**
|
| 162 |
-
```python
|
| 163 |
-
async def _check_policy_violations(self, action_context) -> List[Dict[str, Any]]:
|
| 164 |
-
"""Advanced policy violation detection."""
|
| 165 |
-
violations = []
|
| 166 |
-
|
| 167 |
-
# Guest user admin access detection
|
| 168 |
-
if (action_context.action_type == "admin_access" and
|
| 169 |
-
action_context.actor_id.startswith("guest")):
|
| 170 |
-
violations.append({
|
| 171 |
-
"rule": "admin_access_restriction",
|
| 172 |
-
"message": "Guest user attempting admin access",
|
| 173 |
-
"severity": "high"
|
| 174 |
-
})
|
| 175 |
-
|
| 176 |
-
# Temporal rate limiting with sliding window
|
| 177 |
-
recent_violations = [
|
| 178 |
-
v for v in self.violation_history
|
| 179 |
-
if (v.get("actor_id") == action_context.actor_id and
|
| 180 |
-
datetime.fromisoformat(v["timestamp"]) >
|
| 181 |
-
datetime.utcnow() - timedelta(minutes=5))
|
| 182 |
-
]
|
| 183 |
-
|
| 184 |
-
if len(recent_violations) >= 3:
|
| 185 |
-
violations.append({
|
| 186 |
-
"rule": "rate_limit_exceeded",
|
| 187 |
-
"message": f"Actor {action_context.actor_id} has {len(recent_violations)} recent violations",
|
| 188 |
-
"severity": "medium"
|
| 189 |
-
})
|
| 190 |
-
|
| 191 |
-
return violations
|
| 192 |
-
```
|
| 193 |
-
|
| 194 |
-
#### AnomalyDetector
|
| 195 |
-
|
| 196 |
-
The `AnomalyDetector` employs behavioral analysis and statistical modeling to identify anomalous patterns:
|
| 197 |
-
|
| 198 |
-
**Detection Algorithms:**
|
| 199 |
-
- **Frequency Analysis**: Detects unusual action frequency patterns
|
| 200 |
-
- **Temporal Analysis**: Identifies actions occurring at unusual times
|
| 201 |
-
- **Resource Access Patterns**: Monitors first-time resource access
|
| 202 |
-
- **Privilege Escalation Detection**: Identifies privilege escalation attempts
|
| 203 |
-
|
| 204 |
-
**Behavioral Modeling:**
|
| 205 |
-
```python
|
| 206 |
-
def _update_patterns(self, action_context):
|
| 207 |
-
"""Update behavioral patterns for anomaly detection."""
|
| 208 |
-
actor_id = action_context.actor_id
|
| 209 |
-
actor_data = self.actor_patterns[actor_id]
|
| 210 |
-
|
| 211 |
-
# Update action frequency patterns
|
| 212 |
-
actor_data["action_counts"][action_context.action_type] += 1
|
| 213 |
-
self.global_patterns["action_frequency"][action_context.action_type] += 1
|
| 214 |
-
|
| 215 |
-
# Update resource access patterns
|
| 216 |
-
if action_context.resource_id:
|
| 217 |
-
actor_data["resource_access"][action_context.resource_id] += 1
|
| 218 |
-
self.global_patterns["resource_access"][action_context.resource_id] += 1
|
| 219 |
-
|
| 220 |
-
# Update temporal patterns
|
| 221 |
-
hour = action_context.timestamp.hour
|
| 222 |
-
self.global_patterns["time_patterns"][hour] += 1
|
| 223 |
-
```
|
| 224 |
-
|
| 225 |
-
#### LedgerMonitor
|
| 226 |
-
|
| 227 |
-
The `LedgerMonitor` ensures the integrity of the provenance ledger through continuous validation:
|
| 228 |
-
|
| 229 |
-
**Integrity Checks:**
|
| 230 |
-
- **Chain Integrity**: Validates hash-linked chain structure
|
| 231 |
-
- **Block Completeness**: Ensures no missing blocks in the sequence
|
| 232 |
-
- **Merkle Tree Validation**: Verifies Merkle tree root calculations
|
| 233 |
-
- **Temporal Consistency**: Validates timestamp ordering
|
| 234 |
-
|
| 235 |
-
### Action Framework
|
| 236 |
-
|
| 237 |
-
The action framework provides a comprehensive set of corrective actions with different severity levels and execution modes.
|
| 238 |
-
|
| 239 |
-
#### HaltAction
|
| 240 |
-
|
| 241 |
-
Implements immediate or graceful operation termination:
|
| 242 |
-
|
| 243 |
-
```python
|
| 244 |
-
async def execute(self) -> Dict[str, Any]:
|
| 245 |
-
"""Execute halt action with configurable severity."""
|
| 246 |
-
try:
|
| 247 |
-
self.status = "executing"
|
| 248 |
-
|
| 249 |
-
# Log critical halt decision
|
| 250 |
-
logger.critical(f"HALTING OPERATIONS: {self.halt_reason}")
|
| 251 |
-
logger.critical(f"Affected operations: {self.affected_operations}")
|
| 252 |
-
logger.critical(f"Decision ID: {self.decision.decision_id}")
|
| 253 |
-
|
| 254 |
-
# Execute halt based on level
|
| 255 |
-
if self.halt_level == "immediate":
|
| 256 |
-
# Immediate termination of all affected operations
|
| 257 |
-
await self._immediate_halt()
|
| 258 |
-
elif self.halt_level == "graceful":
|
| 259 |
-
# Graceful shutdown allowing cleanup
|
| 260 |
-
await self._graceful_halt()
|
| 261 |
-
|
| 262 |
-
return {
|
| 263 |
-
"halted_operations": self.affected_operations,
|
| 264 |
-
"halt_timestamp": self.timestamp.isoformat(),
|
| 265 |
-
"halt_reason": self.halt_reason,
|
| 266 |
-
"halt_level": self.halt_level,
|
| 267 |
-
"decision_id": str(self.decision.decision_id)
|
| 268 |
-
}
|
| 269 |
-
except Exception as e:
|
| 270 |
-
self.status = "failed"
|
| 271 |
-
raise
|
| 272 |
-
```
|
| 273 |
-
|
| 274 |
-
#### EscalateAction
|
| 275 |
-
|
| 276 |
-
Implements automated escalation with configurable notification channels:
|
| 277 |
-
|
| 278 |
-
```python
|
| 279 |
-
async def execute(self) -> Dict[str, Any]:
|
| 280 |
-
"""Execute escalation with multi-channel notification."""
|
| 281 |
-
try:
|
| 282 |
-
self.status = "executing"
|
| 283 |
-
|
| 284 |
-
# Log escalation decision
|
| 285 |
-
logger.warning(f"ESCALATING TO {self.escalation_target}: {self.decision.reason}")
|
| 286 |
-
logger.warning(f"Priority: {self.escalation_priority}")
|
| 287 |
-
|
| 288 |
-
# Execute escalation
|
| 289 |
-
escalation_result = {
|
| 290 |
-
"escalation_target": self.escalation_target,
|
| 291 |
-
"escalation_priority": self.escalation_priority,
|
| 292 |
-
"escalation_timestamp": self.timestamp.isoformat(),
|
| 293 |
-
"escalation_context": self.escalation_context,
|
| 294 |
-
"notification_channels": self.notification_channels,
|
| 295 |
-
"decision_id": str(self.decision.decision_id),
|
| 296 |
-
"action_context": self.decision.action_context.model_dump(mode='json')
|
| 297 |
-
}
|
| 298 |
-
|
| 299 |
-
# Send notifications via configured channels
|
| 300 |
-
await self._send_notifications(escalation_result)
|
| 301 |
-
|
| 302 |
-
return escalation_result
|
| 303 |
-
except Exception as e:
|
| 304 |
-
self.status = "failed"
|
| 305 |
-
raise
|
| 306 |
-
```
|
| 307 |
-
|
| 308 |
-
## Security Model
|
| 309 |
-
|
| 310 |
-
### Threat Model
|
| 311 |
-
|
| 312 |
-
The Reflexive Core is designed to protect against the following threat categories:
|
| 313 |
-
|
| 314 |
-
1. **Insider Threats**: Malicious or compromised internal actors
|
| 315 |
-
2. **External Attacks**: Unauthorized external access attempts
|
| 316 |
-
3. **System Compromise**: Compromised system components
|
| 317 |
-
4. **Data Exfiltration**: Unauthorized data access and extraction
|
| 318 |
-
5. **Service Disruption**: DoS attacks and system availability threats
|
| 319 |
-
|
| 320 |
-
### Security Guarantees
|
| 321 |
-
|
| 322 |
-
#### Cryptographic Integrity
|
| 323 |
-
|
| 324 |
-
All reflexive decisions include cryptographic proof hashes that provide:
|
| 325 |
-
|
| 326 |
-
- **Non-repudiation**: Decisions cannot be denied by the system
|
| 327 |
-
- **Integrity Verification**: Any tampering with decisions is detectable
|
| 328 |
-
- **Audit Trail**: Complete, verifiable history of all decisions
|
| 329 |
-
|
| 330 |
-
```python
|
| 331 |
-
def get_decision_hash(self) -> str:
|
| 332 |
-
"""Generate tamper-evident proof hash."""
|
| 333 |
-
content = {
|
| 334 |
-
"decision_id": str(self.decision_id),
|
| 335 |
-
"decision_type": self.decision_type,
|
| 336 |
-
"risk_level": self.risk_level,
|
| 337 |
-
"action_context": self.action_context.model_dump(),
|
| 338 |
-
"reason": self.reason,
|
| 339 |
-
"evidence": self.evidence,
|
| 340 |
-
"escalated_to": self.escalated_to
|
| 341 |
-
}
|
| 342 |
-
content_str = json.dumps(content, sort_keys=True, default=str)
|
| 343 |
-
return hashlib.sha256(content_str.encode()).hexdigest()
|
| 344 |
-
```
|
| 345 |
-
|
| 346 |
-
#### Fail-Safe Design
|
| 347 |
-
|
| 348 |
-
The system implements multiple fail-safe mechanisms:
|
| 349 |
-
|
| 350 |
-
1. **Default Deny**: Unknown or suspicious actions are denied by default
|
| 351 |
-
2. **Graceful Degradation**: System continues operating even when components fail
|
| 352 |
-
3. **Circuit Breakers**: Automatic isolation of failing components
|
| 353 |
-
4. **Rate Limiting**: Protection against resource exhaustion attacks
|
| 354 |
-
|
| 355 |
-
#### Zero-Trust Architecture
|
| 356 |
-
|
| 357 |
-
The Reflexive Core operates on zero-trust principles:
|
| 358 |
-
|
| 359 |
-
- **Continuous Verification**: All actions are verified regardless of source
|
| 360 |
-
- **Least Privilege**: Actions are granted minimum necessary permissions
|
| 361 |
-
- **Defense in Depth**: Multiple layers of security controls
|
| 362 |
-
- **Assume Breach**: System designed to operate securely even when compromised
|
| 363 |
-
|
| 364 |
-
## Implementation Details
|
| 365 |
-
|
| 366 |
-
### Asynchronous Architecture
|
| 367 |
-
|
| 368 |
-
The system is built on an asynchronous, event-driven architecture that provides:
|
| 369 |
-
|
| 370 |
-
- **High Throughput**: Non-blocking event processing
|
| 371 |
-
- **Low Latency**: Immediate response to security events
|
| 372 |
-
- **Scalability**: Horizontal scaling through event distribution
|
| 373 |
-
- **Resilience**: Fault tolerance through async error handling
|
| 374 |
-
|
| 375 |
-
```python
|
| 376 |
-
async def _process_events(self):
|
| 377 |
-
"""Main event processing loop with fault tolerance."""
|
| 378 |
-
while self.is_running:
|
| 379 |
-
try:
|
| 380 |
-
# Wait for events with timeout
|
| 381 |
-
event = await asyncio.wait_for(self.event_queue.get(), timeout=1.0)
|
| 382 |
-
await self._handle_event(event)
|
| 383 |
-
except asyncio.TimeoutError:
|
| 384 |
-
# No events, continue
|
| 385 |
-
continue
|
| 386 |
-
except Exception as e:
|
| 387 |
-
logger.error(f"Error processing reflexive event: {e}")
|
| 388 |
-
# Continue processing despite errors
|
| 389 |
-
```
|
| 390 |
-
|
| 391 |
-
### Dynamic Monitor Registration
|
| 392 |
-
|
| 393 |
-
The system supports dynamic addition and removal of monitors:
|
| 394 |
-
|
| 395 |
-
```python
|
| 396 |
-
def add_monitor(self, monitor: Callable):
|
| 397 |
-
"""Add a monitor function to the reflexive engine."""
|
| 398 |
-
self.monitors.append(monitor)
|
| 399 |
-
logger.info(f"Added monitor: {monitor.__name__}")
|
| 400 |
-
|
| 401 |
-
def remove_monitor(self, monitor: Callable):
|
| 402 |
-
"""Remove a monitor function from the reflexive engine."""
|
| 403 |
-
if monitor in self.monitors:
|
| 404 |
-
self.monitors.remove(monitor)
|
| 405 |
-
logger.info(f"Removed monitor: {monitor.__name__}")
|
| 406 |
-
```
|
| 407 |
-
|
| 408 |
-
### HTTP API Design
|
| 409 |
-
|
| 410 |
-
The RESTful API provides comprehensive access to reflexive core functionality:
|
| 411 |
-
|
| 412 |
-
#### Risk Simulation Endpoint
|
| 413 |
-
|
| 414 |
-
```python
|
| 415 |
-
@router.post("/core/simulate-risk")
|
| 416 |
-
async def simulate_risk_endpoint(request: Request) -> JSONResponse:
|
| 417 |
-
"""Simulate risk scenarios for testing and validation."""
|
| 418 |
-
try:
|
| 419 |
-
body = await request.json()
|
| 420 |
-
reflexive_engine: ReflexiveEngine = request.app.state.reflexive_engine
|
| 421 |
-
|
| 422 |
-
# Simulate the risk scenario
|
| 423 |
-
decision = await reflexive_engine.simulate_risk(body)
|
| 424 |
-
|
| 425 |
-
# Create and execute the corresponding action
|
| 426 |
-
action = ActionFactory.create_action(decision)
|
| 427 |
-
executor = ActionExecutor()
|
| 428 |
-
action_result = await executor.execute_action(action)
|
| 429 |
-
|
| 430 |
-
return JSONResponse(
|
| 431 |
-
status_code=200,
|
| 432 |
-
content={
|
| 433 |
-
"simulation_id": str(decision.decision_id),
|
| 434 |
-
"decision": {
|
| 435 |
-
"decision_id": str(decision.decision_id),
|
| 436 |
-
"decision_type": decision.decision_type,
|
| 437 |
-
"risk_level": decision.risk_level,
|
| 438 |
-
"reason": decision.reason,
|
| 439 |
-
"evidence": decision.evidence,
|
| 440 |
-
"proof_hash": decision.proof_hash,
|
| 441 |
-
"escalated_to": decision.escalated_to,
|
| 442 |
-
"timestamp": decision.timestamp.isoformat()
|
| 443 |
-
},
|
| 444 |
-
"action": {
|
| 445 |
-
"action_id": str(action.action_id),
|
| 446 |
-
"action_type": action.get_action_type(),
|
| 447 |
-
"status": action.status,
|
| 448 |
-
"result": action_result
|
| 449 |
-
},
|
| 450 |
-
"action_context": decision.action_context.model_dump(mode='json')
|
| 451 |
-
}
|
| 452 |
-
)
|
| 453 |
-
except Exception as e:
|
| 454 |
-
logger.error(f"Failed to simulate risk: {e}")
|
| 455 |
-
return JSONResponse(status_code=500, content={"error": str(e)})
|
| 456 |
-
```
|
| 457 |
-
|
| 458 |
-
## Performance Characteristics
|
| 459 |
-
|
| 460 |
-
### Latency Analysis
|
| 461 |
-
|
| 462 |
-
The Reflexive Core is designed for low-latency operation:
|
| 463 |
-
|
| 464 |
-
- **Event Processing**: < 1ms for simple policy checks
|
| 465 |
-
- **Risk Assessment**: < 5ms for complex multi-factor analysis
|
| 466 |
-
- **Action Execution**: < 10ms for halt actions, < 100ms for escalations
|
| 467 |
-
- **End-to-End Response**: < 50ms for critical security events
|
| 468 |
-
|
| 469 |
-
### Throughput Metrics
|
| 470 |
-
|
| 471 |
-
Performance benchmarks under various load conditions:
|
| 472 |
-
|
| 473 |
-
| Load Level | Events/sec | Avg Latency | 95th Percentile | Memory Usage |
|
| 474 |
-
|------------|------------|-------------|-----------------|--------------|
|
| 475 |
-
| Light | 1,000 | 2ms | 5ms | 50MB |
|
| 476 |
-
| Medium | 10,000 | 8ms | 20ms | 200MB |
|
| 477 |
-
| Heavy | 50,000 | 25ms | 60ms | 800MB |
|
| 478 |
-
| Peak | 100,000 | 50ms | 120ms | 1.5GB |
|
| 479 |
-
|
| 480 |
-
### Scalability Characteristics
|
| 481 |
-
|
| 482 |
-
The system exhibits linear scalability characteristics:
|
| 483 |
-
|
| 484 |
-
- **Horizontal Scaling**: Linear scaling with additional processing nodes
|
| 485 |
-
- **Memory Usage**: O(n) where n is the number of active sessions
|
| 486 |
-
- **CPU Usage**: O(m) where m is the number of monitors
|
| 487 |
-
- **Storage**: O(e) where e is the number of events processed
|
| 488 |
-
|
| 489 |
-
## Security Analysis
|
| 490 |
-
|
| 491 |
-
### Attack Surface Analysis
|
| 492 |
-
|
| 493 |
-
The Reflexive Core's attack surface is minimized through:
|
| 494 |
-
|
| 495 |
-
1. **Minimal External Interfaces**: Only essential HTTP endpoints exposed
|
| 496 |
-
2. **Input Validation**: Comprehensive validation of all inputs
|
| 497 |
-
3. **Output Sanitization**: All outputs are sanitized before transmission
|
| 498 |
-
4. **Error Handling**: Secure error handling prevents information leakage
|
| 499 |
-
|
| 500 |
-
### Vulnerability Assessment
|
| 501 |
-
|
| 502 |
-
#### Potential Vulnerabilities
|
| 503 |
-
|
| 504 |
-
1. **Monitor Injection**: Malicious monitors could be injected
|
| 505 |
-
- **Mitigation**: Monitor signature verification and sandboxing
|
| 506 |
-
2. **Decision Manipulation**: Attackers could attempt to manipulate decisions
|
| 507 |
-
- **Mitigation**: Cryptographic proof hashes and immutable audit logs
|
| 508 |
-
3. **Resource Exhaustion**: DoS attacks through excessive event generation
|
| 509 |
-
- **Mitigation**: Rate limiting and circuit breakers
|
| 510 |
-
4. **Information Disclosure**: Sensitive information in logs or responses
|
| 511 |
-
- **Mitigation**: Data classification and access controls
|
| 512 |
-
|
| 513 |
-
#### Security Controls
|
| 514 |
-
|
| 515 |
-
The system implements multiple layers of security controls:
|
| 516 |
-
|
| 517 |
-
1. **Authentication**: All API endpoints require authentication
|
| 518 |
-
2. **Authorization**: Role-based access control for different operations
|
| 519 |
-
3. **Encryption**: All data in transit and at rest is encrypted
|
| 520 |
-
4. **Audit Logging**: Comprehensive audit trail for all operations
|
| 521 |
-
5. **Monitoring**: Continuous monitoring of system security posture
|
| 522 |
-
|
| 523 |
-
### Compliance Considerations
|
| 524 |
-
|
| 525 |
-
The Reflexive Core supports various compliance frameworks:
|
| 526 |
-
|
| 527 |
-
#### SOC 2 Type II
|
| 528 |
-
- **Security**: Comprehensive security controls and monitoring
|
| 529 |
-
- **Availability**: High availability through fault-tolerant design
|
| 530 |
-
- **Processing Integrity**: Cryptographic integrity verification
|
| 531 |
-
- **Confidentiality**: Data encryption and access controls
|
| 532 |
-
- **Privacy**: Data minimization and privacy controls
|
| 533 |
-
|
| 534 |
-
#### ISO 27001
|
| 535 |
-
- **Information Security Management**: Comprehensive ISMS implementation
|
| 536 |
-
- **Risk Management**: Continuous risk assessment and mitigation
|
| 537 |
-
- **Incident Response**: Automated incident detection and response
|
| 538 |
-
- **Business Continuity**: Resilient design for business continuity
|
| 539 |
-
|
| 540 |
-
#### GDPR
|
| 541 |
-
- **Data Protection by Design**: Privacy controls built into the system
|
| 542 |
-
- **Data Minimization**: Only necessary data is collected and processed
|
| 543 |
-
- **Right to Erasure**: Automated data deletion capabilities
|
| 544 |
-
- **Data Portability**: Standardized data export formats
|
| 545 |
-
|
| 546 |
-
## Future Enhancements
|
| 547 |
-
|
| 548 |
-
### Machine Learning Integration
|
| 549 |
-
|
| 550 |
-
Future versions will incorporate machine learning capabilities:
|
| 551 |
-
|
| 552 |
-
1. **Anomaly Detection**: ML-based anomaly detection for novel attack patterns
|
| 553 |
-
2. **Threat Intelligence**: Integration with threat intelligence feeds
|
| 554 |
-
3. **Predictive Analytics**: Predictive threat modeling and risk assessment
|
| 555 |
-
4. **Adaptive Policies**: Self-adjusting policies based on threat landscape
|
| 556 |
-
|
| 557 |
-
### Blockchain Integration
|
| 558 |
-
|
| 559 |
-
Enhanced audit capabilities through blockchain integration:
|
| 560 |
-
|
| 561 |
-
1. **Immutable Audit Logs**: Blockchain-based audit log storage
|
| 562 |
-
2. **Distributed Verification**: Multi-party verification of decisions
|
| 563 |
-
3. **Smart Contracts**: Automated policy enforcement through smart contracts
|
| 564 |
-
4. **Cross-Chain Interoperability**: Integration with multiple blockchain networks
|
| 565 |
-
|
| 566 |
-
### Advanced Analytics
|
| 567 |
-
|
| 568 |
-
Enhanced analytics and reporting capabilities:
|
| 569 |
-
|
| 570 |
-
1. **Real-Time Dashboards**: Live security posture monitoring
|
| 571 |
-
2. **Trend Analysis**: Historical trend analysis and reporting
|
| 572 |
-
3. **Predictive Modeling**: Predictive threat modeling
|
| 573 |
-
4. **Custom Reports**: Configurable reporting and alerting
|
| 574 |
-
|
| 575 |
-
### Integration Ecosystem
|
| 576 |
-
|
| 577 |
-
Expanded integration capabilities:
|
| 578 |
-
|
| 579 |
-
1. **SIEM Integration**: Integration with Security Information and Event Management systems
|
| 580 |
-
2. **SOAR Integration**: Security Orchestration, Automation, and Response integration
|
| 581 |
-
3. **Cloud Provider Integration**: Native integration with cloud security services
|
| 582 |
-
4. **Third-Party Tools**: Integration with popular security tools and platforms
|
| 583 |
-
|
| 584 |
-
## Conclusion
|
| 585 |
-
|
| 586 |
-
The Reflexive Core represents a significant advancement in MCP security architecture, providing autonomous self-monitoring and self-correcting capabilities that address the fundamental limitations of traditional reactive security approaches. Through its sophisticated multi-layered architecture, the system provides:
|
| 587 |
-
|
| 588 |
-
### Key Achievements
|
| 589 |
-
|
| 590 |
-
1. **Autonomous Security**: Self-monitoring and self-correcting capabilities eliminate human bottlenecks
|
| 591 |
-
2. **Cryptographic Integrity**: Tamper-evident audit trails with cryptographic proof
|
| 592 |
-
3. **Real-Time Response**: Sub-50ms response times for critical security events
|
| 593 |
-
4. **Comprehensive Coverage**: Multi-dimensional threat detection and response
|
| 594 |
-
5. **Extensible Architecture**: Dynamic addition of new monitoring and response capabilities
|
| 595 |
-
|
| 596 |
-
### Technical Innovation
|
| 597 |
-
|
| 598 |
-
The Reflexive Core introduces several technical innovations:
|
| 599 |
-
|
| 600 |
-
- **Event-Driven Architecture**: Asynchronous, non-blocking event processing
|
| 601 |
-
- **Multi-Factor Risk Assessment**: Sophisticated risk modeling and decision making
|
| 602 |
-
- **Dynamic Monitor Registration**: Runtime addition of monitoring capabilities
|
| 603 |
-
- **Cryptographic Auditability**: Tamper-evident decision logging
|
| 604 |
-
- **Fail-Safe Design**: Resilient operation even under attack conditions
|
| 605 |
-
|
| 606 |
-
### Security Impact
|
| 607 |
-
|
| 608 |
-
The system provides significant security improvements:
|
| 609 |
-
|
| 610 |
-
- **Reduced Attack Surface**: Automated response eliminates manual intervention delays
|
| 611 |
-
- **Enhanced Visibility**: Comprehensive monitoring and audit capabilities
|
| 612 |
-
- **Improved Compliance**: Built-in support for major compliance frameworks
|
| 613 |
-
- **Proactive Defense**: Predictive threat detection and response
|
| 614 |
-
- **Operational Resilience**: Continued operation under adverse conditions
|
| 615 |
-
|
| 616 |
-
### Future Outlook
|
| 617 |
-
|
| 618 |
-
The Reflexive Core establishes a foundation for next-generation MCP security architectures. Future enhancements will focus on:
|
| 619 |
-
|
| 620 |
-
- **Machine Learning Integration**: Advanced threat detection and response
|
| 621 |
-
- **Blockchain Integration**: Enhanced audit and verification capabilities
|
| 622 |
-
- **Cloud-Native Design**: Optimized for cloud and edge computing environments
|
| 623 |
-
- **Ecosystem Integration**: Seamless integration with existing security tools
|
| 624 |
-
|
| 625 |
-
The Reflexive Core represents a paradigm shift toward autonomous, self-healing security systems that can adapt to evolving threat landscapes while maintaining the highest standards of security, compliance, and operational excellence.
|
| 626 |
-
|
| 627 |
-
---
|
| 628 |
-
|
| 629 |
-
**Document Version**: 1.0
|
| 630 |
-
**Last Updated**: 2024
|
| 631 |
-
**Authors**: FastMCP Development Team
|
| 632 |
-
**Classification**: Technical Whitepaper
|
| 633 |
-
**Distribution**: Internal and Partner Access
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
index.html
CHANGED
|
@@ -122,7 +122,7 @@
|
|
| 122 |
<li><strong>Try the backend:</strong> use the health request below to inspect this Space. It is the registry service, not a general-purpose agent or the calculator example.</li>
|
| 123 |
<li><strong>Build a server:</strong> install the matching fork packages, define your tools, and configure <code>SecurityConfig</code> for the controls your application needs.</li>
|
| 124 |
<li><strong>Connect a client:</strong> point an MCP client at your server’s endpoint. The <a href="https://github.com/PureCipher/xsecuremcp2.0#build-an-mcp-server" target="_blank" rel="noopener noreferrer">server-and-client quickstart</a> demonstrates a tool call and receipt verification.</li>
|
| 125 |
-
<li><strong>Check enforcement:</strong>
|
| 126 |
<li><strong>Share and operate:</strong> use PureCipher Publisher to submit projects to your chosen registry, and the separate xregistry console to manage it. Configure authentication, moderation, and persistent storage for your deployment.</li>
|
| 127 |
</ol>
|
| 128 |
<h2 id="what-this-space-runs">What this Space runs</h2>
|
|
@@ -197,11 +197,11 @@
|
|
| 197 |
<tbody>
|
| 198 |
<tr>
|
| 199 |
<td>GitHub source</td>
|
| 200 |
-
<td><a href="https://github.com/PureCipher/xsecuremcp2.0/commit/
|
| 201 |
</tr>
|
| 202 |
<tr>
|
| 203 |
<td>Package version</td>
|
| 204 |
-
<td><code>0.0.1.
|
| 205 |
</tr>
|
| 206 |
<tr>
|
| 207 |
<td>Build metadata</td>
|
|
|
|
| 122 |
<li><strong>Try the backend:</strong> use the health request below to inspect this Space. It is the registry service, not a general-purpose agent or the calculator example.</li>
|
| 123 |
<li><strong>Build a server:</strong> install the matching fork packages, define your tools, and configure <code>SecurityConfig</code> for the controls your application needs.</li>
|
| 124 |
<li><strong>Connect a client:</strong> point an MCP client at your server’s endpoint. The <a href="https://github.com/PureCipher/xsecuremcp2.0#build-an-mcp-server" target="_blank" rel="noopener noreferrer">server-and-client quickstart</a> demonstrates a tool call and receipt verification.</li>
|
| 125 |
+
<li><strong>Check enforcement:</strong> allow one operation, deny another, and inspect the resulting evidence. See the <a href="https://github.com/PureCipher/xsecuremcp2.0#readme" target="_blank" rel="noopener noreferrer">project README</a> for the security configuration and its boundaries.</li>
|
| 126 |
<li><strong>Share and operate:</strong> use PureCipher Publisher to submit projects to your chosen registry, and the separate xregistry console to manage it. Configure authentication, moderation, and persistent storage for your deployment.</li>
|
| 127 |
</ol>
|
| 128 |
<h2 id="what-this-space-runs">What this Space runs</h2>
|
|
|
|
| 197 |
<tbody>
|
| 198 |
<tr>
|
| 199 |
<td>GitHub source</td>
|
| 200 |
+
<td><a href="https://github.com/PureCipher/xsecuremcp2.0/commit/5bd407c3b7812ee3596ef0e1eea9afa5ecff0534" target="_blank" rel="noopener noreferrer"><code>5bd407c3b781</code></a></td>
|
| 201 |
</tr>
|
| 202 |
<tr>
|
| 203 |
<td>Package version</td>
|
| 204 |
+
<td><code>0.0.1.dev4090+5bd407c3</code></td>
|
| 205 |
</tr>
|
| 206 |
<tr>
|
| 207 |
<td>Build metadata</td>
|
wheels/{fastmcp-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp-0.0.1.dev4090+5bd407c3-py3-none-any.whl}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e444d438ee2c3b531879dd6c94a555d268d9084f18981bf6a06c0fdeb22f47
|
| 3 |
+
size 358043
|
wheels/{fastmcp_remote-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp_remote-0.0.1.dev4090+5bd407c3-py3-none-any.whl}
RENAMED
|
Binary files a/wheels/fastmcp_remote-0.0.1.dev4088+b8f75f12-py3-none-any.whl and b/wheels/fastmcp_remote-0.0.1.dev4090+5bd407c3-py3-none-any.whl differ
|
|
|
wheels/{fastmcp_slim-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp_slim-0.0.1.dev4090+5bd407c3-py3-none-any.whl}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e2fc37acf3083f22ade3c9af463e1de1969c93a50f58a72554f71af6ecfa2a2
|
| 3 |
+
size 1339330
|
wheels/{fastmcp_tasks-0.0.1.dev4088+b8f75f12-py3-none-any.whl → fastmcp_tasks-0.0.1.dev4090+5bd407c3-py3-none-any.whl}
RENAMED
|
Binary files a/wheels/fastmcp_tasks-0.0.1.dev4088+b8f75f12-py3-none-any.whl and b/wheels/fastmcp_tasks-0.0.1.dev4090+5bd407c3-py3-none-any.whl differ
|
|
|