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.
Best use case
fastmcp-server is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using fastmcp-server should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/fastmcp-server/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How fastmcp-server Compares
| Feature / Agent | fastmcp-server | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# 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:**
```python
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:**
```python
@mcp.resource("data://config")
def get_config() -> dict:
"""Return server configuration"""
return {"version": "1.0", "debug": False}
```
**Create a resource template:**
```python
@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:**
```python
@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:**
```python
if __name__ == "__main__":
mcp.run()
# Or with transport options:
# mcp.run(transport="sse", host="0.0.0.0", port=8000)
```
### Using context in tools
```python
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
```python
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 featuresRelated Skills
server-management
Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.
aws-serverless
Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
async-python-patterns
Comprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and async/await for building high-performance, non-blocking systems.
slack-automation
Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.
linear-automation
Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current schemas.
jira-automation
Automate Jira tasks via Rube MCP (Composio): issues, projects, sprints, boards, comments, users. Always search tools first for current schemas.
gitops-workflow
Complete guide to implementing GitOps workflows with ArgoCD and Flux for automated Kubernetes deployments.
github-automation
Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code, and handle deployments programmatically.
github-actions-templates
Production-ready GitHub Actions workflow patterns for testing, building, and deploying applications.
zustand-store-ts
Create Zustand stores following established patterns with proper TypeScript types and middleware.
zod-validation-expert
Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.