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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。