{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_8s72da9jve76","handle":"ersilia-mcp","url":"https://wellknown.network/agents/ersilia-mcp","links":{"self":"https://wellknown.network/agents/ersilia-mcp/record.json","html":"https://wellknown.network/agents/ersilia-mcp","markdown":"https://wellknown.network/agents/ersilia-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ersilia-mcp","status":"https://wellknown.network/api/v1/agents/ersilia-mcp/status","claim":"https://wellknown.network/agents/ersilia-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ersilia-mcp/claim.json","badge":"https://wellknown.network/agents/ersilia-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ersilia-mcp/history","tools":"https://wellknown.network/api/v1/agents/ersilia-mcp/tools"},"ard":{"identifier":"urn:air::server:ersilia-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ersilia-mcp","summary":"A Model Context Protocol (MCP) server for searching, fetching, serving, and running Ersilia Model Hub models","description":"# MCP server for the Ersilia Model Hub\n\nA [Model Context Protocol](https://modelcontextprotocol.io) server built on the\nofficial FastMCP SDK. It lets MCP clients search the Ersilia Model Hub catalog\nand fetch, serve, and run its AI/ML models, all over stdio.\n\n| Primitive | Name                  | Description                                                  |\n| --------- | --------------------- | ----------------------------------------------------------- |\n| Tool      | `search_model`        | Searches the Ersilia model hub catalog by keyword.          |\n| Tool      | `fetch_model`         | Downloads a model to the local machine.                     |\n| Tool      | `check_model_fetched` | Reports whether a model has already been fetched.           |\n| Tool      | `serve_model`         | Starts a fetched model so it can accept predictions.        |\n| Tool      | `generate_inputs`     | Samples example inputs from a served model.                 |\n| Tool      | `predict`             | Runs predictions with a served model and writes a CSV.      |\n| Tool      | `close_model`         | Stops a served model and frees its resources.               |\n| Tool      | `delete_model`        | Deletes a fetched model from local storage.                 |\n\nA typical workflow is `search_model` → `fetch_model` → `serve_model` → `predict`\n→ `close_model`. You can optionally call `generate_inputs` after serving to\nsample example inputs to feed into `predict`, and `delete_model` to remove the\nmodel from local storage.\n\n## Installation\n\nEnsure you have the following installed:\n* [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html#regular-installation) (miniconda is fine)\n* [Docker](https://docs.docker.com/get-docker/)\n* [git](https://git-scm.com/install/source)\n\nClone the repository locally using git:\n```bash\ngit clone git@github.com:ersilia-os/ersilia-mcp.git\n```\n\nCreate a new virtual conda environment, activate it, and install the necessary packages:\n…","publisher":{"name":"Ersilia Open Source Initiative","url":null},"homepage":null,"repository":null,"version":"1.0.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:ersilia-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"}],"categories":["dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ersilia-mcp","registry":"pypi","observedAt":"2026-09-15T14:26:54.388Z","publishedAt":"2026-08-28T08:36:40.100496Z","latestVersion":"1.0.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ersilia-mcp","url":"https://pypi.org/project/ersilia-mcp/","firstSeenAt":"2026-09-09T15:21:42.994Z","fetchedAt":"2026-09-15T14:24:50.231Z","normalizedAt":"2026-09-15T14:24:50.231Z"}]},"firstSeenAt":"2026-09-09T15:21:42.994Z","updatedAt":"2026-09-15T14:26:54.388Z"}