Advertise
MCP.so
Sign In

MCPHub: The Unified Hub for MCP Servers

@samanhappy

RepositoryHomepage

Basic information

Category

Other

License

Apache-2.0

Transports

stdio

Author

samanhappy

About MCPHub: The Unified Hub for MCP Servers

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

#mcp#mcp-server#mcp-hub#mcp-router

MCPHub: The Unified Hub for MCP Servers config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcphub": {
      "command": "docker",
      "args": [
        "run",
        "-p",
        "3000:3000",
        "-v",
        "./mcp_settings.json:/app/mcp_settings.json",
        "-v",
        "./data:/app/data",
        "samanhappy/mcphub"
      ]
    }
  }
}

MCPHub: The Unified Hub for MCP Servers tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCPHub?

MCPHub is a unified hub that manages and scales multiple MCP (Model Context Protocol) servers by organizing them into flexible Streamable HTTP (SSE) endpoints, supporting access to all servers, individual servers, or logical server groups.

How to use MCPHub?

Create a mcp_settings.json file with your MCP server definitions, deploy via Docker with a single docker run command, and connect AI clients (Claude Desktop, Cursor, etc.) to endpoints like http://localhost:3000/mcp. Manage servers from a web dashboard or from the terminal using the included CLI.

Key features of MCPHub

  • Centralized management via a unified dashboard
  • Flexible routing to all servers, groups, or individual servers
  • Granular group visibility for Tools, Prompts, and Resources
  • AI-powered tool discovery using vector semantic search
  • Hot-swappable configuration without downtime
  • OAuth 2.0 support in both client and server modes
  • Docker-ready deployment with two image variants

Use cases of MCPHub

  • Run and monitor multiple MCP servers from a single dashboard
  • Expose server groups with tailored tool visibility to different AI clients
  • Deploy a production hub with PostgreSQL database and OAuth authentication
  • Discover and call tools from a terminal using the built-in CLI

Frequently asked questions

1

How do I deploy MCPHub?

Run `docker run -p 3000:3000 -v ./mcp_settings.json:/app/mcp_settings.json -v ./data:/app/data samanhappy/mcphub`. Two image variants are available: `latest` (includes Node.js, Python, uv/uvx, Git) and `latest-full` (adds Rust toolchain, Docker Engine, and Playwright browsers).

2

What storage options does MCPHub support?

By default MCPHub uses a file-based `mcp_settings.json`. For production environments, it supports Database Mode with PostgreSQL using TypeORM and pgvector for Smart Routing.

3

Can I manage MCPHub from the terminal?

Yes. The `mcphub` binary doubles as a CLI for the running hub, supporting commands like `mcphub servers list`, `mcphub servers add`, `mcphub tools list`, and `mcphub call`. No extra install is needed.

4

How do I secure MCPHub endpoints?

MCP endpoints require authentication by default. You can set an admin password via the `ADMIN_PASSWORD` environment variable, use OAuth 2.0, or enable bearer key authentication. Unauthenticated MCP access can be allowed by disabling bearer authentication in the Keys section.

Comments

More Other MCP servers

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K
Advertise