Simplify MCP server management with a proxy for aggregation authentication configuration and Docker support
MCP Simple Gateway is a versatile proxy server designed to facilitate seamless communication between various Model Context Protocol (MCP) clients and their corresponding data sources or tools via standardized APIs. This server bridges the gap, enabling a wide range of AI applications like Claude Desktop, Continue, Cursor, and others to interact with diverse backend services efficiently.
MCP Simple Gateway introduces several key features that make it indispensable for integrating and managing multiple MCP servers:
The architecture of the MCP Simple Gateway incorporates a two-tiered model: an entry point where all requests are aggregated and forwarded, followed by a tier behind it that handles the actual service interaction. The protocol flow is structured to authenticate users, route their requests appropriately, and ensure secure data exchange.
graph TD
A[AI Application] -->|MCP Client| B[MCP Protocol]
B --> C[MCP Server]
C --> D[Data Source/Tool]
style A fill:#e1f5fe
style C fill:#f3e5f5
style D fill:#e8f5e8
graph TD
A[AI Application] -->|MCP Client| B[MCP Server]
B --> C[Data Source/Tool]
C -->|API Responses| B
B --> D[Client-Server Communication]
style A fill:#e1f5fe
style C fill:#f3e5f5
To quickly start using the MCP Simple Gateway, you can deploy it via command-line interface or Docker Compose. Below are detailed steps to follow:
With package managers such as npm
, you can easily launch the gateway by running:
npx mcp-simple-gateway --config config.json
Alternatively, if you prefer a Docker container, use docker-compose.yml
for setup:
services:
mcp-gateway:
image: ghcr.io/denwakeup/mcp-simple-gateway:latest
volumes:
- ./config.json:/app/config.json
ports:
- '3000:3000'
environment:
- CONFIG_PATH=/app/config.json
AI applications such as Claude Desktop can leverage MCP Simple Gateway to streamline real-time data fetching processes. By integrating this gateway, the application can query and process data from various sources, enhancing its performance and responsiveness.
{
"mcpServers": {
"weather_data": {
"command": "npx",
"args": ["@modelcontextprotocol/server-weather"],
"env": {
"API_KEY": "your-api-key"
}
},
"news_feed": {
"command": "npx",
"args": ["@modelcontextprotocol/server-newsFeed"],
"env": {
"API_KEY": "your-secret-api-key"
}
}
}
}
For applications requiring asynchronous data processing, the gateway supports streaming data via HTTP. This feature enables seamless transfer of large datasets without blocking user interfaces.
MCP Simple Gateway is compatible with multiple clients, ensuring broad applicability across different AI platforms:
The MCP Simple Gateway supports a range of clients with varying levels of compatibility:
MCP Client | Resources | Tools | Prompts | Status |
---|---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ | Full Support |
Continue | ✅ | ✅ | ✅ | Full Support |
Cursor | ❌ | ✅ | ❌ | Tools Only |
Configuring the MCP Simple Gateway involves setting up a JSON file according to the specified schema provided in the README. Key parameters include logging levels, authentication tokens, and proxy options.
{
"proxyServer": {
"options": {
"logLevel": "debug",
"logPretty": true,
"authTokens": ["your-auth-token"]
}
},
"mcpServers": {
"[serverName]": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-[name]"],
"proxyOptions": {
"authTokens": ["server-specific-token"]
}
}
}
}
A1: You should use token-based authentication as provided by the authTokens
parameter in your configuration file.
A2: Currently, certain clients like Cursor only support tools; Claude Desktop and Continue fully support all features.
A3: The default port is 3000, but it can be configured as needed via environment variables in Docker setups or command-line arguments.
A4: Streamable HTTP (SSE) and stdio support ensure efficient and continuous data flow between the client and backend.
A5: While specific improvements were not detailed, recent updates include improved error handling, logging enhancements, and better compatibility with new MCP clients.
Contributors can join the development effort by following these steps:
Detailed instructions are available in the CONTRIBUTING.md
file.
Explore further into the MCP ecosystem with resources like official documentation, community forums, and relevant tools:
By integrating the MCP Simple Gateway, developers can ensure robust and scalable AI application development leveraging standardized protocols.
AI Vision MCP Server offers AI-powered visual analysis, screenshots, and report generation for MCP-compatible AI assistants
Analyze search intent with MCP API for SEO insights and keyword categorization
Learn how to use MCProto Ruby gem to create and chain MCP servers for custom solutions
MCP server for accessing and managing IMDB data with notes, summaries, and tools
Learn how to try Model Context Protocol server with MCP Client and Cursor tools efficiently
Connects n8n workflows to MCP servers for AI tool integration and data access