Poke MCP Production Server
A production-ready Pokémon MCP server that enables users to get comprehensive Pokémon information and simulate realistic turn-based battles. Features enterprise-grade authentication, monitoring, rate limiting, and serverless deployment capabilities.
README
Poke MCP Production Server
A production-ready Pokémon MCP (Model Context Protocol) server with enterprise features:
- ✅ FastMCP with HTTP Transport - RESTful API access to MCP tools
- 🔒 Authentication - API key-based security
- 📈 Monitoring - Prometheus metrics and health checks
- 📝 Structured Logging - JSON-formatted logs with structlog
- ⚡ Rate Limiting - Protect against abuse
- 🚀 Vercel Deployment - Serverless deployment with continuous integration
- 🔐 SSH Tunneling - Secure remote access configuration
Features
MCP Tools
-
get_pokemon_info - Comprehensive Pokémon information
- Base stats, types, abilities (with descriptions)
- Moves with effects (first 10)
- Full evolution chain
-
simulate_battle - Realistic Pokémon battle simulation
- Core battle mechanics (type effectiveness, status effects)
- Turn-based combat with detailed battle log
- Winner determination
Production Features
- Authentication: Bearer token API key authentication
- Rate Limiting: Configurable request limits per time window
- Monitoring: Prometheus metrics for requests, latency, and tool calls
- Logging: Structured JSON logs with request tracing
- CORS: Configurable cross-origin resource sharing
- Health Checks:
/healthendpoint for monitoring - Environment Configuration: Flexible environment-based settings
Quick Start
Prerequisites
- Python 3.11+
- uv (recommended) or pip
- Vercel account (for deployment)
Local Development
- Clone the repository
git clone https://github.com/patrickcarmichael/poke-mcp-production.git
cd poke-mcp-production
- Install dependencies
# Using uv (recommended)
uv sync
# Or using pip
pip install -r requirements.txt
- Configure environment
cp .env.example .env
# Edit .env with your settings
- Run the server
# For MCP stdio mode (local testing)
python server.py
# For HTTP mode (production)
uvicorn api.index:app --reload --host 0.0.0.0 --port 8000
- Test the server
# Health check
curl http://localhost:8000/health
# Protected endpoint (requires API key)
curl -H "Authorization: Bearer your-api-key" http://localhost:8000/status
Deployment
See DEPLOYMENT.md for comprehensive deployment instructions including:
- Vercel deployment
- Environment variable configuration
- SSH tunnel setup for remote access
- Continuous deployment setup
- Production monitoring
Configuration
All configuration is managed through environment variables. See .env.example for all available options.
Key Configuration Options
| Variable | Description | Default |
|---|---|---|
API_KEY |
Authentication key | (required) |
ALLOWED_ORIGINS |
CORS allowed origins | http://localhost:* |
LOG_LEVEL |
Logging level | INFO |
RATE_LIMIT_REQUESTS |
Max requests per window | 100 |
RATE_LIMIT_WINDOW |
Time window in seconds | 60 |
ENABLE_METRICS |
Enable Prometheus metrics | true |
API Endpoints
Public Endpoints
GET /- Server informationGET /health- Health checkGET /metrics- Prometheus metrics (if enabled)
Protected Endpoints (Require API Key)
POST /mcp- MCP tool execution endpointGET /status- Detailed server status
Authentication
All protected endpoints require a Bearer token:
curl -H "Authorization: Bearer YOUR_API_KEY" https://your-server.vercel.app/status
Monitoring
Prometheus Metrics
The server exposes Prometheus-compatible metrics at /metrics:
http_requests_total- Total HTTP requests by method, endpoint, and statushttp_request_duration_seconds- Request latency histogrammcp_tool_calls_total- MCP tool invocations by tool name and statusmcp_tool_duration_seconds- Tool execution durationpokeapi_requests_total- PokeAPI requests by endpoint and statusactive_connections- Current active connections
Logging
Structured JSON logs include:
- Request/response details
- Tool execution tracking
- Error tracking with stack traces
- Performance metrics
SSH Tunneling for Remote Access
See SSH_TUNNELING.md for detailed instructions on:
- Setting up SSH tunnels to access your deployed server
- Configuring Claude Desktop and other MCP clients
- Security best practices
- Troubleshooting
Architecture
poke-mcp-production/
├── api/
│ └── index.py # Vercel serverless handler
├── src/
│ ├── __init__.py
│ ├── auth.py # Authentication logic
│ ├── battle_utils.py # Battle simulation utilities
│ ├── config.py # Configuration management
│ ├── constants.py # Type effectiveness, constants
│ ├── logger.py # Structured logging setup
│ ├── middleware.py # CORS, rate limiting, logging
│ ├── monitoring.py # Prometheus metrics
│ └── pokeapi_client.py # PokeAPI integration
├── server.py # Main MCP server (stdio mode)
├── vercel.json # Vercel configuration
├── pyproject.toml # Project metadata
├── requirements.txt # Python dependencies
└── .env.example # Environment template
Development
Testing
# Install dev dependencies
uv sync --extra dev
# Run tests (when implemented)
pytest
# Code formatting
black .
# Linting
ruff check .
# Type checking
mypy src/
Adding New Tools
- Add tool function to
server.py:
@mcp.tool()
async def my_new_tool(param: str) -> Dict[str, Any]:
"""Tool description."""
# Implementation
return {"result": "data"}
- Add monitoring and logging as needed
- Update documentation
Security Considerations
- API Keys: Always use strong, randomly generated API keys
- CORS: Configure
ALLOWED_ORIGINSfor production - Rate Limiting: Adjust limits based on expected usage
- HTTPS: Always use HTTPS in production (Vercel provides this)
- SSH Tunnels: Use key-based authentication, not passwords
- Secrets: Never commit
.envfiles or secrets to git
Troubleshooting
Server Won't Start
- Check Python version:
python --version(must be 3.11+) - Verify all dependencies are installed
- Check
.envfile configuration
Authentication Failures
- Verify API key is set in environment
- Check Authorization header format:
Bearer YOUR_KEY - Ensure CORS settings allow your origin
Rate Limiting Issues
- Adjust
RATE_LIMIT_REQUESTSandRATE_LIMIT_WINDOW - Check client IP address handling
- Review logs for rate limit events
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details
Acknowledgments
- PokeAPI - Pokémon data source
- FastMCP - MCP server framework
- Model Context Protocol - MCP specification
- Original poke-mcp implementations by NaveenBandarage and ChiragAgg5k
Support
For issues, questions, or contributions:
- Open an issue on GitHub
- Check DEPLOYMENT.md for deployment help
- Review SSH_TUNNELING.md for remote access setup
Roadmap
- [ ] Full MCP protocol integration in Vercel endpoint
- [ ] WebSocket support for real-time updates
- [ ] Caching layer for PokeAPI responses
- [ ] Additional battle mechanics
- [ ] Team management tools
- [ ] Database integration for persistent data
- [ ] GraphQL API option
- [ ] Docker deployment option
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.