--- title: Kalanos LeRobot & Robotics Dataset Search MCP emoji: ๐Ÿ”Ž colorFrom: green colorTo: gray sdk: gradio sdk_version: 6.27.0 python_version: '3.12' app_file: app.py license: apache-2.0 short_description: Search LeRobot datasets, quality reports and episodes tags: - robotics - lerobot - data-quality - mcp - dataset-search - model-context-protocol pinned: true --- # Kalanos LeRobot & Robotics Dataset Search MCP Search LeRobot and robotics datasets, inspect existing data quality reports, and find episodes to review in your AI assistant. ## What you can do - **Find relevant robotics datasets.** Search by task, objects, scene, robot, format, license, episode count and dataset size, using available metadata and labels. - **Inspect LeRobot quality reports.** See recorded decisions, assessment coverage and limitations before choosing what to review. - **Trace findings to episodes.** Explore recorded issues and evidence, then search within a dataset for published task, object and scene labels. - **Compare assessments with context.** Ask your assistant to compare report dates, revisions and measured scope instead of treating scores as interchangeable. This is read-only access to existing public reports. It does not run new grading, download dataset shards or publish reports. Labels and scores do not establish task success, hardware health or training performance. ## Setup ### Connect through Hugging Face 1. Open the app tab and use the MCP badge to add this Space to your MCP tools. 2. In [Hugging Face MCP settings](https://huggingface.co/settings/mcp), choose your client and follow its generated setup instructions. Hugging Face requires a token with read access for this route. 3. Refresh or restart your client and confirm the Kalanos tools are available. See the [Hugging Face setup guide](https://huggingface.co/docs/hub/en/spaces-mcp-servers). ### Connect a remote MCP client directly Use the public endpoint **https://mcp.kalanos.ai/mcp**, transport **Streamable HTTP**, and **no authentication**. No API key is needed for the direct public endpoint. Enable the server and refresh its tools. For the adapter hosted in this Space, open **Use via API โ†’ MCP** in the app footer and copy the connection URL shown there. [Client-specific setup and usage](https://kalanos.ai/mcp) covers Claude, ChatGPT and other MCP clients. Availability depends on your account and workspace settings. ## Sample questions - "Find robotics datasets for pick-and-place. Show robot type, episode count and available quality reports. Explain missing metadata." - "Search for lerobot/pusht, then use the returned report ID to show its current assessment. What was measured, what was not measured, and what needs review?" - "Find the reports for lerobot/pusht and lerobot/aloha_sim_insertion_human. Compare their recorded findings and coverage. Explain whether the assessments are comparable." - "For lerobot/berkeley_autolab_ur5, fetch the current report and its recorded episode findings. Which episodes should I inspect first, and what evidence supports that?" - "Within [dataset ID], find episodes matching [task or object]. Distinguish published labels from quality findings, and explain any missing label coverage." For reliable report lookup, search or list first and use the returned report_id. Fetch the current report_revision before requesting findings. Results are paginated; missing evidence is not a pass. ## Available tools - list_datasets: browse public LeRobot and robotics datasets already processed by Kalanos, with metadata and report filters. - search_datasets: find LeRobot and robotics datasets by keyword, ranked relevance and dataset filters. - search_combined_datasets: discover datasets using metadata together with published task, object and scene labels; returns datasets, not a global episode list. - get_report: retrieve an existing data quality report with recorded decisions, scores, assessment coverage and limitations. Use the report_id returned by search or list. - get_findings: retrieve recorded episode-level quality findings and evidence at the exact report_revision returned by get_report. - search_episodes: find episodes to review within one dataset using published task, object and scene labels. Labels are separate from quality findings. [Browse public reports](https://hub.kalanos.ai/datasets) ยท [Request a new assessment](https://kalanos.ai/submit-dataset) ## Adapter implementation notes Deploy the contents of this directory as the root of a **new public Gradio Space** (CPU Basic). Do not replace the grader's root app.py or README.md. No secrets or HF token are needed by the adapter. Six fixed typed tools forward to https://mcp.kalanos.ai/mcp anonymously. The checked-in upstream schema validates arguments; new upstream tools never become exposed automatically. The result is the upstream MCP CallToolResult envelope as JSON text; upstream isError becomes a Gradio/MCP tool error. Preserve dates, scope, revision, missing evidence and pagination. Upstream errors are returned as evidence, not new grading results. `get_findings` requires the report_revision returned by `get_report`. Use report_id returned by search/list: the upstream short dataset example lerobot/pusht returned not_found in live QA. Limits: four concurrent reads, queue size 16, 30-second total upstream timeout. Anonymous upstream rate limits are shared by this Space's egress IP. This is not a cached mirror or historical archive. Sleeping CPU Spaces can cause cold starts. No remote URL parameter, authentication passthrough, dataset downloads, grading, publishing, or filesystem tools are exposed. Run `python -m unittest discover -s tests -v` after installing requirements. `python app.py` launches both the UI and MCP. Inspect `/gradio_api/mcp/schema` and the footer's MCP connection instructions. The HF MCP badge is platform-generated after deployment; adding a README tag alone does not enable MCP. `search_combined_datasets` exposes Hub combined dataset discovery. Deploy the upstream tool first, then this adapter; refresh client tool discovery. Existing episode search still requires dataset scope. Combined search returns dataset pages, not a global episode cursor. Optional `facets=true` requests full-result facets/counts. With facets disabled, totals may be null; follow `page.next_page` / `has_more`.