MCP OpenAPI Template
A template for building MCP servers from OpenAPI specifications, enabling automatic conversion of any REST API into LLM-accessible tools with built-in authentication and validation.
README
MCP OpenAPI Template
A template for building MCP (Model Context Protocol) servers from OpenAPI specifications.
This template provides a production-ready foundation for creating MCP servers that expose any REST API with an OpenAPI specification to LLM-powered tools.
Features
- Dynamic Tool Generation: Automatically creates MCP tools from OpenAPI specs
- Auth Gateway Integration: Centralized authentication via Auth Gateway
- Dual Transport: Supports both
stdio(local) andsse(remote) transports - Configurable Validation: Customizable ID patterns and input validation
- Tool Policies: Risk-based policies for blocking/logging operations
- Docker Ready: Production-ready Dockerfile and docker-compose
Quick Start
1. Clone/Use Template
# Using GitHub template feature (recommended)
# Click "Use this template" on GitHub
# Or clone directly
git clone https://github.com/jesusperezdeveloper/mcp_openapi_template my-api-mcp
cd my-api-mcp
2. Initialize Your Service
python -m scripts.init_service \
--name "github" \
--display-name "GitHub" \
--base-url "https://api.github.com" \
--openapi-url "https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json"
3. Configure Auth Gateway
Edit .env with your Auth Gateway credentials:
AUTH_GATEWAY_URL=https://your-auth-gateway.com
AUTH_GATEWAY_API_KEY=your-api-key
4. Download OpenAPI Spec
python -m scripts.fetch_openapi
5. Run the Server
# Local mode (stdio)
PYTHONPATH=vendor python -m src.server
# Remote mode (SSE)
MCP_TRANSPORT=sse PYTHONPATH=vendor python -m src.server
Project Structure
mcp_openapi_template/
├── src/
│ ├── server.py # Main MCP server
│ ├── config.py # Configuration loader
│ ├── openapi_tools.py # Dynamic tool generator
│ ├── auth_gateway.py # Auth Gateway integration
│ ├── validation.py # Input validation
│ └── tool_policies.py # Risk policies
├── config/
│ ├── service.yaml # Service configuration
│ ├── mcp.local.json # Local MCP config
│ └── mcp.remote.json # Remote MCP config
├── scripts/
│ ├── fetch_openapi.py # Download OpenAPI spec
│ └── init_service.py # Initialize new service
├── examples/
│ └── trello/ # Complete Trello example
├── openapi/ # OpenAPI specs (downloaded)
├── vendor/mcp/ # Vendorized MCP SDK
├── Dockerfile
└── docker-compose.yml
Configuration
service.yaml
The main configuration file (config/service.yaml) defines:
service:
name: "myservice"
display_name: "My Service"
api:
base_url: "https://api.example.com"
openapi_spec_url: "https://api.example.com/openapi.json"
tool_prefix: "myservice"
auth:
gateway_endpoint: "/credentials/myservice"
credentials_format:
- name: "api_key"
query_param: "key"
validation:
id_pattern: "^[a-zA-Z0-9]+$"
policies:
blocked_patterns:
- "delete_organization"
Environment Variables
| Variable | Required | Description |
|---|---|---|
AUTH_GATEWAY_URL |
Yes | Auth Gateway URL |
AUTH_GATEWAY_API_KEY |
Yes | API Key for Auth Gateway |
API_BASE_URL |
No | Override API base URL |
MCP_TRANSPORT |
No | stdio (default) or sse |
MCP_PORT |
No | Port for SSE mode (default: 8000) |
Authentication Flow
- User obtains JWT from Auth Gateway (login)
- User calls
set_auth_token(jwt)in the MCP - MCP fetches API credentials from Auth Gateway
- Credentials are cached for the session
- User can now use all available tools
Adding Custom Helper Tools
See examples/trello/helpers.py for a complete example of adding user-friendly wrapper tools.
# In src/helpers.py
def register_helper_tools(mcp, auth_params, client_factory, require_auth):
@mcp.tool(description="My custom tool")
async def my_tool(param: str) -> dict:
require_auth()
# Implementation
pass
Docker Deployment
# Build with OpenAPI spec
docker build \
--build-arg OPENAPI_SPEC_URL="https://api.example.com/openapi.json" \
-t my-mcp .
# Run
docker run -p 8000:8000 --env-file .env my-mcp
Examples
See the examples/ directory for complete configurations:
- Trello: Full configuration with helper tools, validation, and policies
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.
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.
Neon Database
MCP server for interacting with Neon Management API and databases