About MCP Servers
MCP Servers is a collection of MCP server implementations in Python, Go, and Rust for VS Code and other MCP clients. The Python server is production-ready, while the Go and Rust implementations remain in progress.
Key features
- 01Python server with FastAPI
- 02SSE and JSON-RPC endpoints
- 03Error handling and logging
- 04Prometheus metrics and health checks
- 05Go and Rust server implementations in progress
Use cases
- 01Connect VS Code to an MCP server over HTTP/SSE
- 02Run the Python server with Docker Compose
- 03Develop or contribute implementations in Go and Rust
MCP support
The repository provides MCP servers for clients such as VS Code, with SSE and JSON-RPC interfaces. The Python implementation is complete; Go and Rust versions are still under development.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Servers
A collection of Model Context Protocol (MCP) servers implemented in different programming languages for use with VS Code and other MCP clients.
Overview
This repository contains MCP server implementations in three languages:
| Server | Status | Description |
|---|---|---|
| Python MCP Server | ✅ Production Ready | FastAPI-based MCP server with comprehensive features |
| Go MCP Server | ⚠️ In Progress | Go-based MCP server using centralmind/gateway |
| Rust MCP Server | ⚠️ In Progress | Terraform-focused MCP server using tfmcp |
What is MCP?
The Model Context Protocol (MCP) is a protocol designed for communication between AI agents and tools/services. It enables AI systems to interact with various tools and services through a standardized interface.
Getting Started
Prerequisites
- Docker and Docker Compose
- VS Code (for client integration)
Running the Servers
To run all servers:
docker-compose up
To run only the Python server (recommended for production use):
docker-compose up mcp-python
Server Status
Python MCP Server (✅ Production Ready)
The Python MCP server is fully operational and production-ready:
- Implements the complete Model Context Protocol
- Provides SSE and JSON-RPC endpoints
- Includes comprehensive error handling and logging
- Features Prometheus metrics for monitoring
- Includes health checks for container orchestration
Endpoints:
GET /health- Health check endpointGET /sse- Server-Sent Events endpoint for real-time communicationPOST /- Main MCP endpoint for JSON-RPC requests
Go MCP Server (⚠️ In Progress)
The Go MCP server is currently in development:
- Implements the core MCP protocol features
- Uses PostgreSQL for database operations
- Provides JSON-RPC and SSE endpoints
- Includes advanced code assistance features:
- Code completion for multiple languages
- Code analysis and diagnostics
- Documentation lookup
- Requires further testing and optimization
Endpoints:
GET /sse- SSE endpoint (needs further configuration)GET /- API documentation
Rust MCP Server (⚠️ In Progress)
The Rust MCP server requires further development:
- Based on the tfmcp tool for Terraform integration
- Currently doesn't fully support the HTTP interface needed for MCP
- Requires further investigation and potentially custom development
VS Code Integration
VS Code can connect to the MCP servers using the SSE/HTTP MCP Protocol. Add the following to your VS Code settings.json:
{
"mcp.python.serverUrl": "http://localhost:8080",
"mcp.python.enableAutoConnect": true
}
Contributing
Contributions are welcome! Here are some ways you can contribute:
- Improve the existing server implementations
- Add new server implementations in other languages
- Enhance documentation and examples
- Report bugs and suggest features
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.