Atrax
Proxy that aggregates multiple MCP servers and presents them as a unified interface, allowing clients to access resources from multiple servers transparently.
README
Atrax: MCP Server Aggregation Proxy v0.1.0
. . __
.| |. _____ _/ |_____________ ___ ___
|| || \__ \\ __\_ __ \__ \ \ \/ /
\\()// / __ \| | | | \// __ \_> <
.={}=. (____ /__| |__| (____ /__/\_ \
/ /`'\ \ \/ \/ \/
` \ / '
`' MCP PROXY FOR THE WEB v0.1.0
Atrax is a proxy for Model Context Protocol (MCP) servers that aggregates multiple MCP servers and presents them as a single unified interface. The name comes from the funnel-web spider, reflecting how it funnels resources from multiple servers into one.
Features
- Resource Aggregation: Combine resources from multiple servers with configurable conflict resolution
- Transparent Proxying: Present a unified MCP server interface to clients
- Protocol Compliance: Strict adherence to the MCP protocol specification
- Modular Design: Clear separation of concerns between components
- Multiple Transport Types: Support for STDIO, HTTP/SSE, and Docker transports
- Enhanced Error Handling: Detailed error reporting with contextual information
- Web Integration: HTTP/SSE transport for browser and web-based clients
- Authentication Support: Token-based authentication for securing server access
Quick Start
# Clone the repository
git clone https://github.com/yourusername/atrax.git
cd atrax
# Setup development environment
direnv allow # Sets up Python venv and pre-commit
npm install
# Build the project
npm run build
# Run the server (no authentication)
npm run serve
# Run with token authentication
npm run serve:auth
# Run smoke tests
npm run test:smoke
Documentation Map
- DEVELOPMENT.md: Development environment setup and workflow
- GUIDELINES.md: Project guidelines and coding standards
- MCP_SDK_INTEGRATION.md: MCP SDK integration guide
- HTTP_SSE_TRANSPORT.md: HTTP/SSE transport implementation and usage
- TOKEN_AUTH.md: Token authentication guide and usage
- DIRENV.md: Using direnv for environment management
- CLAUDE.md: Quick reference for common commands
- VERSION_MANAGEMENT.md: Guidelines for version management
Examples
The examples/ directory contains example server implementations:
- Memory server: A simple MCP server that stores a knowledge graph in memory
- Echo server: A basic MCP server that echoes back requests
- HTTP Echo server: An MCP server that uses HTTP/SSE transport to communicate
Run examples with:
# STDIO-based servers
npm run memory-server
npm run echo-server
# HTTP/SSE-based server
npm run http-echo-server
# Client examples
npm run echo-client # Connect to STDIO Echo server
npm run memory-client # Connect to STDIO Memory server
npm run http-echo-client # Connect to HTTP/SSE Echo server
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.