RouterMCP

RouterMCP is a powerful MCP (Model Context Protocol) gateway that aggregates multiple upstream MCP servers into a single unified interface. Give your AI assistants access to all your tools through one connection.

Choose Your Path

Quick Start

Using the CLI (Self-Hosted)

npm install -g routermcp
routermcp config
routermcp

Using RouterMCP Cloud

1. Sign up at routermcp.com
2. Create a project and add your MCP servers
3. Connect your AI client using the provided endpoint

Key Features

• Server Aggregation - Combine multiple MCP servers into one unified gateway
• Tool Filtering - Control which tools are exposed using include/exclude patterns
• Multiple Transports - Support for stdio, HTTP/SSE, and Streamable HTTP
• Code Mode - Execute JavaScript in a sandboxed environment
• Cloudflare Tunnels - Expose local servers to the internet securely
• Team Collaboration - Share projects and servers with your team (Cloud)
• OAuth Integration - Handle OAuth flows for upstream servers (Cloud)

What is MCP?

The Model Context Protocol is an open standard for connecting AI assistants to external tools and data sources. MCP servers provide tools, resources, and prompts that AI clients can use.

RouterMCP acts as a gateway that:

1. Connects to multiple upstream MCP servers
2. Aggregates their tools into a single namespace
3. Exposes them through a unified MCP interface
4. Handles authentication, filtering, and routing

Next Steps