MCP Proxy Server
Aggregates multiple MCP resource servers into a single interface.
MCP Proxy Server
An MCP proxy server that aggregates and serves multiple MCP resource servers through a single interface. This server acts as a central hub that can:
- Connect to and manage multiple MCP resource servers
- Expose their combined capabilities through a unified interface
- Handle routing of requests to appropriate backend servers
- Aggregate responses from multiple sources
Features
Resource Management
- Discover and connect to multiple MCP resource servers
- Aggregate resources from all connected servers
- Maintain consistent URI schemes across servers
- Handle resource routing and resolution
Tool Aggregation
- Expose tools from all connected servers
- Route tool calls to appropriate backend servers
- Maintain tool state and handle responses
Prompt Handling
- Aggregate prompts from all connected servers
- Route prompt requests to appropriate backends
- Handle multi-server prompt responses
Configuration
The server requires a JSON configuration file that specifies the MCP servers to connect to. Copy the example config and modify it for your needs:
cp config.example.json config.json
Example config structure:
{
"servers": [
{
"name": "Server 1",
"transport": {
"command": "/path/to/server1/build/index.js"
}
},
{
"name": "Server 2",
"transport": {
"command": "server2-command",
"args": ["--option1", "value1"],
"env": ["SECRET_API_KEY"]
}
},
{
"name": "Example Server 3",
"transport": {
"type": "sse",
"url": "http://localhost:8080/sse"
}
}
]
}
The config file must be provided when running the server:
MCP_CONFIG_PATH=./config.json mcp-proxy-server
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
For development with continuous run:
# Stdio
npm run dev
# SSE
npm run dev:sse
Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"mcp-proxy": {
"command": "/path/to/mcp-proxy-server/build/index.js",
"env": {
"MCP_CONFIG_PATH": "/absolute/path/to/your/config.json",
"KEEP_SERVER_OPEN": "1"
}
}
}
}
KEEP_SERVER_OPENwill keep the SSE running even if a client disconnects. Useful when multiple clients connects to the MCP proxy.
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Related Servers
GitHub Actions
An MCP Server for the GitHub Actions API, enabling AI assistants to manage and operate GitHub Actions workflows.
Unified MCP & A2A Server
A Google Apps Script server that unifies Model Context Protocol (MCP) and Agent2Agent (A2A) for Google Workspace users.
kintone
An MCP server for integrating with the kintone REST API. Supports CRUD operations, file management, comments, and status updates.
Mobile Xray MCP
Take screenshots and analyze mobile apps with AI assistance directly from your IDE.
chuk-mcp
A Python client for the Model Context Protocol (MCP), an open standard for connecting AI assistants to external data and tools.
Coding Standards
An MCP server for enforcing coding standards and best practices.
Xcode MCP
Integrate with Xcode to build and manage your projects.
Tailwind Svelte Assistant
Provides documentation and code snippets for SvelteKit and Tailwind CSS.
MCP_Agent:RE
Fetches requirements and defect data from the TAPD platform to provide data support for AI clients.
mcp-graphql
A GraphQL server that supports the Model Context Protocol (MCP), enabling Large Language Models (LLMs) to interact with GraphQL APIs through schema introspection and query execution.