MCP Auth Example
Demonstrates a FastMCP server with Bearer token authentication via Nginx and fine-grained authorization via Envoy and OPA.
README
MCP Auth Example
This project demonstrates a FastMCP server with both authenticated and unauthenticated endpoints. Bearer token authentication is enforced at the Nginx proxy layer. Envoy acts as a reverse proxy, forwarding requests to the MCP server and integrating with Open Policy Agent (OPA) for fine-grained authorization decisions. The repository includes example clients and a Docker setup for running all components together.
Features
- FastMCP server with and without authentication
- Example Python clients for both endpoints
- Docker Compose setup with Nginx, Envoy, and OPA integration
Project Structure
.
├── Dockerfile # Dockerfile for MCP server
├── README.md
├── client.py # Example client for both endpoints
├── docker-compose.yml # Docker Compose setup (Nginx, Envoy, OPA, MCP)
├── proxy
│ ├── envoy # Envoy config
│ │ ├── Dockerfile
│ │ ├── entrypoint.sh
│ │ └── envoy.yaml
│ ├── nginx.conf # Nginx config for Bearer auth
│ └── policy.rego # OPA policy for Envoy
├── pyproject.toml # Python project config
├── server.py # Unauthenticated MCP server (port 8000)
└── uv.lock
Quick Start
1. Install Dependencies
Install Python dependencies (requires uv):
uv sync
2. Build and Start Services
Build and start all services using Docker Compose:
docker compose up --build -d
- MCP server (unauthenticated): http://localhost:8000/mcp/
- MCP server (authenticated, via Nginx): http://localhost/mcp/
3. Test the Clients
Unauthenticated
uv run client.py
Authenticated
Edit client.py to use the authenticated endpoint and provide a valid token.
How It Works
server.py: Runs a FastMCP server on port 8000 (no auth).client.py: Example client for both endpoints, supports custom authentication.proxy/: Contains Nginx and Envoy configs for authentication and policy enforcement.
Requirements
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.