Geenie MCP Proxy Server
Acts as an intermediary between Claude Desktop and Amazon's MCP server to handle authentication, token management, and subscription-based tool filtering. It provides a secure layer for managing access to Amazon tools while facilitating seamless communication between the client and the model server.
README
Geenie MCP Proxy Server
The Geenie MCP proxy server sits between Claude Desktop and Amazon's MCP server, handling authentication, token management, and subscription-based tool filtering.
Quick Start
1. Install Dependencies
npm install
2. Set Up Environment
Copy .env.example to .env and fill in your credentials:
cp .env.example .env
For local development, the mock Amazon MCP server endpoints are pre-configured.
3. Run the Servers
You'll need two terminal windows:
Terminal 1 - Mock Amazon MCP Server:
npm run dev:mock
Terminal 2 - Geenie Proxy Server:
npm run dev
The mock server runs on port 9000, and the proxy runs on port 3000.
4. Test the Health Check
curl http://localhost:3000/health
5. Test the MCP Proxy
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{"method": "tools/list", "params": {}}'
You should see a list of tools returned from the mock Amazon server.
Project Structure
geenie-proxy/
├── src/
│ ├── index.ts # Server entry point
│ ├── config/
│ │ └── env.ts # Environment configuration
│ ├── routes/
│ │ ├── health.ts # Health check endpoints
│ │ └── mcp.ts # MCP proxy route
│ └── utils/
│ └── logger.ts # Pino logger setup
├── tests/
│ └── mocks/
│ └── amazon-server.ts # Mock Amazon MCP server
└── package.json
Development Phases
✅ Phase 1: Basic Proxy (Current)
- [x] Project setup with TypeScript
- [x] Fastify server with CORS
- [x] Health check endpoint
- [x] Basic MCP proxy route
- [x] Mock Amazon MCP server
⏳ Phase 2: Authentication (Next)
- [ ] API key validation middleware
- [ ] Subscription status checking
- [ ] Supabase integration
- [ ] Caching layer
⏳ Phase 3: Token Management
- [ ] Amazon token refresh logic
- [ ] Multi-account handling
- [ ] Token expiry checks
⏳ Phase 4: Tool Filtering
- [ ] Subscription tier restrictions
- [ ] Global tool blacklist
- [ ] Disabled tools injection
⏳ Phase 5: Production Ready
- [ ] Token encryption
- [ ] Rate limiting
- [ ] Error handling improvements
- [ ] Railway deployment
Available Scripts
npm run dev- Start proxy server with hot reloadnpm run dev:mock- Start mock Amazon MCP servernpm run build- Compile TypeScript to JavaScriptnpm start- Run production buildnpm test- Run tests (coming soon)
Environment Variables
See .env.example for all available configuration options.
Testing
Currently using a mock Amazon MCP server that simulates:
tools/list- Returns available MCP toolstools/call- Simulates tool execution with mock data
Next Steps
- Add API key validation (Phase 2)
- Integrate with Supabase for user/subscription data
- Implement Amazon token refresh logic
- Add subscription-based tool filtering
- Deploy to Railway
License
MIT
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.