FastMCP is the fast, Pythonic framework for building Model Context Protocol (MCP) servers, clients, and apps. Originally created by Jeremiah Lowin and maintained by PrefectHQ, FastMCP 1.0 was adopted into the official Anthropic MCP Python SDK in 2024, and the standalone FastMCP project (now at v3) remains the most widely used way to ship MCP servers in Python — the project reports powering roughly 70% of MCP servers across all languages. FastMCP turns ordinary Python functions into MCP tools, resources, prompts, and apps via decorators, auto-generates JSON Schemas from type hints, handles transport negotiation (stdio, Streamable HTTP, SSE), and ships first-class OAuth/OIDC authentication, server composition and proxying, OpenAPI/FastAPI import, a CLI for running and installing servers into Claude Desktop / Claude Code / Cursor / ChatGPT / Gemini CLI / Goose, middleware, lifespan management, elicitation, sampling, progress reporting, OpenTelemetry, and a client library and apps runtime for building interactive UIs rendered inside MCP host conversations.
FastMCP is listed with 6 APIs on the APIs.io network. Tagged areas include MCP, Python, Framework, Open Source, and AI Agents.
FastMCP’s developer surface includes developer portal, getting-started guide, documentation, changelog, release notes, FAQ, and 28 more developer resources.
19.5/100emerging▬ flatAgent6/100agent awareFront door AI6/6
dominant
Heartbeat93/100
alive
library · Apache License 2.0
Full breakdown ↓
scored 2026-11-13 · rubric v0.28.0 · Show this score on your site →
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for
this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero:
never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and
several others — scorable at all.
The six quality facets above are damped to 85 points between them,
because the conditional facet above carries the other
15. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 85% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/fastmcp/"><img src="https://apis.io/badge/fastmcp/card.svg" alt="FastMCP on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Machine-Readable Auth+10 pts — a served openid-configuration/oauth-authorization-server carrying `issuer` (served), else the securitySchemes class in the provider OpenAPIs — bound (mutualTLS, DPoP, Signature) > negotiable (oauth2 authorizationCode/clientCredentials, openIdConnect) > bearer (http bearer, apiKey) Ask about this →
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented) Ask about this →
Stable Error Semantics+8 pts — OpenAPI $refs a shared error schema across 4xx/5xx responses (verified), else common[].type includes ErrorCatalog / ErrorCodes / DeclineCodes Ask about this →
Rate-Limit Signaling+7 pts — OpenAPI responses document X-RateLimit-* / RateLimit headers (verified), else a rate_limits artifact or RateLimits link (documented) Ask about this →
11 more unmet checks in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.
Not sure how this applies to your stack? Ask about any one item. Kin Lane reads every question, looks at your profile and your situation, and replies with what a fix would take — scoped to that one area, priced up front, yours whether you ship it or not. Ask a question →
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
The FastMCP Server is the Python entry point for exposing tools, resources, prompts, and apps to any Model Context Protocol client. Developers instantiate a `FastMCP` server obj...
The FastMCP Client is a Python client library for talking to any MCP server — local or remote — with full protocol coverage. It supports calling tools, reading resources, gettin...
FastMCP ships a complete authentication and authorization layer for MCP servers. Servers can verify tokens, terminate OAuth flows directly, or proxy to an external OAuth or OIDC...
FastMCP can generate an MCP server directly from an existing OpenAPI 3.x description or a FastAPI application, turning every HTTP operation into an MCP tool with auto-generated ...
The FastMCP CLI is a developer command-line tool for running, inspecting, installing, and debugging MCP servers built with FastMCP. It can launch servers under any transport, in...
Permit.io and Eunomia integrations for policy-driven authorization.
OpenAPI and FastAPI import
Generate an MCP server directly from an OpenAPI spec or FastAPI app so existing REST APIs become agent-callable in one step.
Server composition and proxying
Mount servers under namespaces, proxy to other MCP servers (including local, filesystem, and skills providers), and transform tools/prompts/resources between surfaces.
Middleware and dependency injection
Wrap requests with middleware and inject runtime dependencies into tool handlers.
Lifespan, context, logging, progress, elicitation
Full MCP protocol coverage including lifespan management, request context, structured logging, progress reporting, and user elicitation.
LLM sampling and background tasks
Client APIs for LLM sampling against the host model and for spawning background tasks.
Production-grade primitives for paginated responses, server versioning, pluggable storage backends, and component icons.
CLI for running and installing servers
Run, inspect, install, and generate FastMCP servers and clients; one-line install into Claude Desktop, Claude Code, Cursor, ChatGPT, and Gemini CLI.
Apps runtime
Approval, Choice, Form Input, and File Upload providers plus prefab, generative, and low-level HTML apps rendered inside MCP host conversations.
Anthropic-adopted lineage
FastMCP 1.0 was incorporated into the official Anthropic MCP Python SDK; the standalone FastMCP project (now v3) continues as the leading Python framework, reportedly powering ~...
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.