fastmcp-server
Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment. Use when creating Python MCP servers or integrating AI models with external tools and data.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 3.3w
- Forks
- 3.9k
01 前言 Front Matter
- name
- fastmcp-server
- tags
- [ "FastMCP", "MCP", "Python", "AI", "Tools", "Server", "Authentication", "Providers" ]
- author
- FastMCP Community
- license
- MIT
- version
- 1.0.0
- description
- Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment. Use when creating Python MCP servers or integrating AI models with external tools and data.
- dependencies
- []
02 资源文件 30
- 参考文档references/authentication/full-oauth-server.md5.1 KB
- 参考文档references/authentication/oauth-proxy.md31.3 KB
- 参考文档references/authentication/oidc-proxy.md9.8 KB
- 参考文档references/authentication/remote-oauth.md14.0 KB
- 参考文档references/authentication/token-verification.md17.3 KB
- 参考文档references/authorization.md13.1 KB
- 参考文档references/context/background-tasks.md10.1 KB
- 参考文档references/context/dependency-injection.md12.4 KB
- 参考文档references/context/mcp-context.md16.7 KB
- 参考文档references/context/user-elicitation.md11.4 KB
- 参考文档references/features/client-logging.md3.3 KB
- 参考文档references/features/icons.md4.3 KB
- 参考文档references/features/lifespans.md3.6 KB
- 参考文档references/features/middleware.md28.9 KB
- 参考文档references/features/opentelemetry.md9.5 KB
- 参考文档references/features/pagination.md4.2 KB
- 参考文档references/features/progress-reporting.md2.2 KB
- 参考文档references/features/sampling.md19.6 KB
- 参考文档references/features/storage-backends.md9.4 KB
- 参考文档references/features/versioning.md25.9 KB
- 参考文档references/getting-started/installation.md3.8 KB
- 参考文档references/getting-started/quickstart.md12.7 KB
- 参考文档references/getting-started/upgrade-guide.md6.4 KB
- 参考文档references/providers/custom.md15.5 KB
- 参考文档references/providers/filesystem.md17.8 KB
- 参考文档references/providers/local.md3.9 KB
- 参考文档references/providers/skills.md11.0 KB
- 参考文档references/server/resources-and-templates.md56.1 KB
- 参考文档references/server/server-class.md8.1 KB
- 参考文档references/server/tools.md41.3 KB
03 SKILL.md 正文
FastMCP 3.0 Server Development
Complete reference for building production-ready MCP (Model Context Protocol) servers with FastMCP 3.0 - the fast, Pythonic framework for connecting LLMs to tools and data.
When to use this skill
Use FastMCP Server when:
- Creating a new MCP server in Python
- Adding tools, resources, or prompts to an MCP server
- Implementing authentication (OAuth, OIDC, token verification)
- Setting up middleware for logging, rate limiting, or authorization
- Configuring providers (local, filesystem, skills, custom)
- Building production MCP servers with telemetry and storage
- Upgrading from FastMCP 2.x to 3.0
Key areas covered:
- Tools & Resources (CORE): Decorators, validation, return types, templates
- Context & DI (CORE): MCP context, dependency injection, background tasks
- Authentication (SECURITY): OAuth, OIDC, token verification, proxy patterns
- Authorization (SECURITY): Scope-based and role-based access control
- Middleware (ADVANCED): Request/response pipeline, built-in middleware
- Providers (ADVANCED): Local, filesystem, skills, and custom providers
- Features (ADVANCED): Pagination, sampling, storage, OpenTelemetry, versioning
Quick reference
Core patterns
Create a server with tools:
from fastmcp import FastMCP
mcp = FastMCP("MyServer")
@mcp.tool
def add(a: int, b: int) -> int:
"""Add two numbers"""
return a + b
Create a resource:
@mcp.resource("data://config")
def get_config() -> dict:
"""Return server configuration"""
return {"version": "1.0", "debug": False}
Create a resource template:
@mcp.resource("users://{user_id}/profile")
def get_user_profile(user_id: str) -> dict:
"""Get a user's profile by ID"""
return fetch_user(user_id)
Create a prompt:
@mcp.prompt
def review_code(code: str, language: str = "python") -> str:
"""Review code for best practices"""
return f"Review this {language} code:\n\n{code}"
Run the server:
if __name__ == "__main__":
mcp.run()
# Or with transport options:
# mcp.run(transport="sse", host="0.0.0.0", port=8000)
Using context in tools
from fastmcp import FastMCP, Context
mcp = FastMCP("MyServer")
@mcp.tool
def process_data(uri: str, ctx: Context) -> str:
"""Process data with logging and progress"""
ctx.info(f"Processing {uri}")
ctx.report_progress(0, 100)
data = ctx.read_resource(uri)
ctx.report_progress(100, 100)
return f"Processed: {data}"
Authentication setup
from fastmcp import FastMCP
from fastmcp.server.auth import BearerAuthProvider
auth = BearerAuthProvider(
jwks_uri="https://your-provider/.well-known/jwks.json",
audience="your-api",
issuer="https://your-provider/"
)
mcp = FastMCP("SecureServer", auth=auth)
Key concepts
Tools
Functions exposed as executable capabilities for LLMs. Decorated with @mcp.tool. Support Pydantic validation, async, custom return types, and annotations (readOnlyHint, destructiveHint).
Resources & Templates
Static or dynamic data sources identified by URIs. Resources use fixed URIs (data://config), templates use parameterized URIs (users://{id}/profile). Support MIME types, annotations, and wildcard parameters.
Context
The Context object provides access to MCP features within tools/resources: logging, progress reporting, resource access, LLM sampling, user elicitation, and session state.
Dependency Injection
Inject values into tool/resource functions using Depends(). Supports HTTP requests, access tokens, custom dependencies, and generator-based cleanup patterns.
Providers
Control where components come from. LocalProvider (default, decorator-based), FileSystemProvider (load from Python files on disk), SkillsProvider (packaged bundles), or custom providers.
Authentication & Authorization
Multiple auth patterns: token verification (JWT, JWKS), OAuth proxy, OIDC proxy, remote OAuth, and full OAuth server. Authorization via scopes on components and middleware.
Middleware
Intercept and modify requests/responses. Built-in middleware for rate limiting, error handling, logging, and response size limits. Custom middleware via @mcp.middleware.
Using the references
Detailed documentation is organized in the references/ folder:
Getting Started
- getting-started/installation.md - Install FastMCP, optional dependencies, verify setup
- getting-started/upgrade-guide.md - Migrate from FastMCP 2.x to 3.0
- getting-started/quickstart.md - First server, tools, resources, prompts, running
Server
- server/server-class.md - FastMCP server configuration, transport options, tag filtering
- server/tools.md - Tool decorator, parameters, validation, return types, annotations
- server/resources-and-templates.md - Resources, templates, URIs, wildcards, MIME types
Context
- context/mcp-context.md - Context object, logging, progress, resource access, sampling
- context/background-tasks.md - Long-running operations with task support
- context/dependency-injection.md - Depends(), custom deps, HTTP request, access tokens
- context/user-elicitation.md - Request structured input from users during execution
Features
- features/icons.md - Custom icons for tools, resources, prompts, and servers
- features/lifespans.md - Server lifecycle management and startup/shutdown hooks
- features/client-logging.md - Send log messages to MCP clients
- features/middleware.md - Request/response pipeline, built-in and custom middleware
- features/pagination.md - Paginate large component lists
- features/progress-reporting.md - Report progress for long-running operations
- features/sampling.md - Request LLM completions from the client
- features/storage-backends.md - Memory, file, and Redis storage for caching and tokens
- features/opentelemetry.md - Distributed tracing and observability
- features/versioning.md - Version components and filter by version ranges
Authentication
- authentication/token-verification.md - JWT, JWKS, introspection, static keys, custom
- authentication/remote-oauth.md - Delegate auth to upstream OAuth provider
- authentication/oauth-proxy.md - Full OAuth proxy with PKCE, client management
- authentication/oidc-proxy.md - OpenID Connect proxy with auto-discovery
- authentication/full-oauth-server.md - Complete built-in OAuth server
Authorization
- authorization.md - Scope-based access control, middleware authorization, patterns
Providers
- providers/local.md - Default provider, decorator-based component registration
- providers/filesystem.md - Load components from Python files on disk
- providers/skills.md - Package and distribute component bundles
- providers/custom.md - Build custom providers for any component source
Version history
v1.0.0 (February 2026)
- Initial release covering FastMCP 3.0 (release candidate)
- 30 reference files across 7 categories
- Complete coverage of tools, resources, context, auth, providers, and features
04 同仓库更多 Skills
wealthville-pool-scoring
Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.
technical-debt-auditor
Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.
readonly-sql-guard
Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.