OAuth MCP Server
A complete OAuth 2.1 server implementation for FastMCP with PKCE support, enabling secure authentication and authorization flows. Provides authorization code exchange, token management, and refresh capabilities for building authenticated MCP applications.
README
OAuth MCP Server
A complete OAuth 2.1 server implementation for FastMCP with PKCE support.
⚠️ Security Warning
This is an advanced authentication pattern. Building a secure OAuth server requires deep expertise in authentication protocols, cryptography, and security best practices. The FastMCP documentation strongly recommends using Remote OAuth or OAuth Proxy instead unless you have compelling requirements.
See OAUTH_README.md for complete documentation.
Quick Start
Installation
# Install dependencies
uv sync
Run the Server
python main.py
The server will start on http://localhost:8000 with a demo OAuth client registered.
Test the OAuth Flow
In a separate terminal:
python oauth_client_example.py
This will demonstrate the complete OAuth 2.1 flow including:
- PKCE challenge/verifier generation
- Authorization code exchange
- Access token usage
- Token refresh
Test Dynamic Client Registration
Register new OAuth clients dynamically at runtime:
python test_dcr.py
Or use curl:
curl -X POST http://localhost:8000/oauth/register \
-H "Content-Type: application/json" \
-d '{
"redirect_uris": ["http://localhost:5000/callback"],
"client_name": "My App",
"scope": "read write"
}'
The server will respond with a client_id and client_secret that you can use immediately.
Test New OAuth Endpoints
Test all the new OAuth 2.0/2.1 endpoints:
python test_new_endpoints.py
This tests:
- OAuth Authorization Server Metadata discovery
- Token revocation (RFC 7009)
- Token introspection (RFC 7662)
- UserInfo endpoint
Demo Credentials
OAuth Client:
- Client ID:
demo_client - Client Secret:
demo_secret
Demo User:
- Username:
demo_user - Password:
demo_password
Project Structure
oauth_mcp/
├── main.py # FastMCP server with OAuth
├── oauth_provider.py # OAuth 2.1 server implementation
├── oauth_client_example.py # Complete OAuth flow demo
├── test_dcr.py # Dynamic Client Registration test
├── test_new_endpoints.py # Tests for all new OAuth endpoints
├── client.py # Original simple client (no auth)
├── OAUTH_README.md # Complete documentation
└── README.md # This file
Features
✅ Full OAuth 2.1 implementation
✅ PKCE (Proof Key for Code Exchange)
✅ Authorization code flow
✅ Token refresh with rotation
✅ Token revocation (RFC 7009)
✅ Token introspection (RFC 7662)
✅ Scope validation
✅ State parameter for CSRF protection
✅ Dynamic Client Registration (DCR) - RFC 7591
✅ OAuth Authorization Server Metadata (RFC 8414)
✅ OAuth Protected Resource Metadata (RFC 9470)
✅ UserInfo endpoint for user profile
Documentation
See OAUTH_README.md for:
- Detailed architecture
- Security considerations
- Production deployment guide
- Database schema
- Testing strategies
- Troubleshooting
References
- FastMCP OAuth Documentation
- OAuth 2.1 Specification
- PKCE Specification (RFC 7636)
- Dynamic Client Registration (RFC 7591)
License
Copyright Anysphere Inc.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.