# tadata-org/fastapi_mcp

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

Repository: https://github.com/tadata-org/fastapi_mcp
Canonical: https://ross.abutalabs.com/products/fastapi_mcp
Homepage: https://fastapi-mcp.tadata.com/
Language: Python
License: MIT
License Family: permissive
Topics: ai, claude, cursor, fastapi, llm, mcp, mcp-server, mcp-servers, modelcontextprotocol, openapi, windsurf, authentication, authorization
Last push: 2025-11-24T14:51:54+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 40, longevity 38
- inputs: {"age_days": 543, "days_push": 282, "days_rel": 401, "gap_med": 4, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11988, forks 964 (observed 2026-08-28T04:10:50.604195+00:00)

## What it is
FastAPI-MCP is a Python library that automatically exposes FastAPI endpoints as Model Context Protocol (MCP) tools, preserving request/response schemas and documentation. It supports authentication via existing FastAPI dependencies and can mount the MCP server onto the same app or deploy it separately.

## Use cases
- turn my fastapi api into mcp tools for claude
- expose rest endpoints to ai agents via mcp
- add an mcp server to an existing fastapi app
- connect cursor or windsurf to my api
- secure mcp tools with fastapi auth dependencies
- auto-generate mcp server from openapi schemas

## When to choose
- you already have a FastAPI app and want AI agents to call its endpoints
- you want zero-config MCP generation with schema and docs preservation
- you need authentication on MCP tools reusing FastAPI dependencies

## When to avoid
- you need custom MCP tools that don't map to API endpoints
- your backend isn't FastAPI/Python
- you need fine-grained control over tool definitions beyond endpoint metadata

## Facets
- artifact type: library
- maturity: active
- function: mcp, api-framework, auth, authorization, middleware
- domain: artificial-intelligence, large-language-models, web-development, backend, apis
- platform: python, self-hosted
- tags: fastapi, mcp-server, openapi, llm-tools, claude, cursor, windsurf, asgi, ai-agents, web-server

## Member repositories
- tadata-org/fastapi_mcp (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:50.604195+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:15:01.387866+00:00, confidence not recorded.
  - readme: https://github.com/tadata-org/fastapi_mcp (fetched 2026-08-28T04:10:50.604195+00:00, sha 0af3f1721182)
  - homepage: https://fastapi-mcp.tadata.com/ (fetched 2026-08-29T08:12:49.023879+00:00, sha 67f318229091)
  - site_page: https://fastapi-mcp.tadata.com/getting-started/installation (fetched 2026-08-29T08:12:49.025792+00:00, sha 113dd6eb0b9d)
  - site_page: https://fastapi-mcp.tadata.com/getting-started/quickstart (fetched 2026-08-29T08:12:49.027532+00:00, sha 08dcb60aa1b6)
  - site_page: https://fastapi-mcp.tadata.com/getting-started/FAQ (fetched 2026-08-29T08:12:49.029521+00:00, sha 01536ade3545)
  - site_page: https://fastapi-mcp.tadata.com/getting-started/best-practices (fetched 2026-08-29T08:12:49.031292+00:00, sha af2a7801e620)
  - registry_pypi: https://pypi.org/pypi/fastapi_mcp/json (fetched 2026-08-29T08:12:49.032984+00:00, sha 5d61aaeae6b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.