MCPHub — Centralized MCP Server Management Hub

What it is

MCPHub is a centralized management platform for multiple MCP (Model Context Protocol) servers. It provides a web dashboard for adding, configuring, and monitoring MCP servers, with smart routing to direct requests to the right server. It supports hot-swap configuration changes and OAuth 2.0 authentication.

MCPHub targets teams running multiple MCP servers who need a unified control plane. Instead of managing individual server configurations and connections, MCPHub consolidates everything into a single interface.

How it saves time or tokens

Managing MCP servers individually means editing JSON config files, restarting processes, and tracking which server handles which tool. MCPHub replaces this with a web UI where you add servers, configure routing, and monitor health in real time. Hot-swap configuration means you can add or remove servers without restarting the hub. OAuth 2.0 authentication secures multi-user access without custom auth code.

How to use

1. Deploy MCPHub with Docker:

docker run -p 3000:3000 samanhappy/mcphub

1. Open http://localhost:3000 and log in with the default admin account.

1. Add your MCP servers via the dashboard. Configure routing rules and authentication for each server.

1. Point your AI tools (Claude Desktop, Cursor) to MCPHub as a single MCP endpoint.

Example

{
  "mcpServers": {
    "mcphub": {
      "command": "docker",
      "args": [
        "run", "-p", "3000:3000",
        "samanhappy/mcphub"
      ]
    }
  }
}

After MCPHub is running, add individual MCP servers through the web dashboard:

# Example: Adding a filesystem MCP server via MCPHub API
curl -X POST http://localhost:3000/api/servers \
  -H 'Content-Type: application/json' \
  -d '{"name": "filesystem", "command": "npx", "args": ["@anthropic/mcp-filesystem", "/data"]}'

Related on TokRepo

• MCP Integrations — Docker-based MCP server configurations
• AI Agent Tools — Tools for building and managing AI agents

This tool integrates with standard development workflows and requires minimal configuration to get started. It is available as open-source software with documentation and community support through the official repository. The project follows semantic versioning for stable releases.

For teams evaluating this tool, the key advantage is reducing manual work in repetitive tasks. The automation provided by the built-in features means less custom code to maintain and fewer integration points to manage. This translates directly to lower maintenance costs and faster iteration cycles.

Common pitfalls

• The default admin credentials should be changed immediately after first login; running MCPHub with default credentials on a public network is a security risk.
• MCPHub adds a routing layer between your AI tools and MCP servers; expect slightly higher latency compared to direct MCP connections.
• Hot-swap configuration applies to server additions and removals; some routing rule changes may require a brief reconnection from connected clients.