burugo/one-mcp

A centralized reverse-proxy platform for MCP servers — manage, group, and export as Skills from a single endpoint.

What it solves

One MCP provides a centralized way to manage multiple Model Context Protocol (MCP) services. Instead of configuring services individually, users can discover, install, and monitor them from a single proxy interface, reducing the complexity of managing various MCP providers.

How it works

It acts as a proxy server built with Go and React. It supports various MCP transport methods including stdio, SSE, and streamable HTTP. The system allows users to group multiple services into a single endpoint, which can then be exported as "Skills" for tools like Claude Code and Droid.

Who it’s for

Developers and AI power users who use MCP-compatible services and want a unified dashboard for configuration, usage analytics, and service organization.

Highlights

  • Centralized Management: Install and configure MCP services from a marketplace or custom sources via a web UI.
  • Service Grouping: Combine multiple services into one endpoint to simplify integration with AI agents.
  • Real-time Analytics: Track request rates, response times, and system health.
  • Enterprise-ready Features: Includes role-based access control (RBAC), OAuth (GitHub/Google), and support for multiple databases (SQLite, MySQL, PostgreSQL).
  • Flexible Deployment: Available via Homebrew, Docker, or manual installation.

Related

  • Project
    samanhappy/mcphub

    A unified management hub for Model Context Protocol (MCP) servers that organizes them into streamable HTTP endpoints with centralized routing and AI-powered tool discovery.

  • 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
    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
    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.

  • 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.