samanhappy/mcphub

A unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.

What it solves

MCPHub provides a centralized way to manage, scale, and route traffic to multiple Model Context Protocol (MCP) servers. It eliminates the need to configure each server individually in AI clients, instead offering a single, unified hub that can organize servers into groups and provide secure, authenticated access via HTTP/SSE endpoints.

How it works

The project acts as a proxy and management layer for MCP servers. It organizes servers into flexible routing paths (e.g., /mcp/{group} or /mcp/{server}), allowing AI clients to connect to a single endpoint. It uses a dashboard for configuration and a CLI for terminal-based management. For advanced discovery, it implements "Smart Routing" using vector semantic search to help AI models find the right tool across multiple servers.

Who it’s for

Developers and AI engineers who deploy multiple MCP servers and need a centralized management dashboard, secure sharing options, and a simplified connection method for AI clients like Claude Desktop or Cursor.

Highlights

  • Unified Dashboard: Monitor and control all MCP servers from one place.
  • Flexible Routing: Access all servers, specific groups, or individual servers via HTTP/SSE.
  • Smart Routing: AI-powered tool discovery using vector semantic search.
  • Secure Access: Supports OAuth 2.0, bearer authentication, and social logins (GitHub/Google).
  • Hot-Swappable Config: Update or add servers without needing to restart the system.
  • Tool Result Compression: Reduces large text outputs to save bandwidth and tokens before they reach the client.
  • Database Mode: PostgreSQL support for production environments, including pgvector for semantic search.

Related

  • Project
    burugo/one-mcp

    A centralized proxy and management platform for Model Context Protocol (MCP) services that allows users to discover, install, and monitor services from a single interface.

  • Project
    mcp-router/mcp-router

    A desktop application for centralized management of Model Context Protocol (MCP) servers, allowing users to organize servers into projects and workspaces while maintaining local data privacy.

  • Project
    tbxark/mcp-proxy

    An MCP proxy server that aggregates multiple Model Context Protocol servers into a single HTTP entry point, simplifying tool and resource management.

  • Project
    1mcp-app/agent

    A unified runtime for MCP servers that aggregates multiple servers into one process and provides a progressive discovery workflow to prevent agent context sprawl.

  • Project
    microsoft/mcp

    A collection of Model Context Protocol (MCP) servers and core tooling that standardizes how AI agents and LLMs connect to Microsoft services and external data sources.