MCPMate

English | |

Your progressive MCP management partner.

> Import MCP once. Start simple, then add profiles, per-client tools, and setup modes as your workflow grows.

>

> MCPMate is a local-first assistant that grows with you—not just another config file editor.

MCPMate sits between your AI apps and MCP servers so you manage connections once and send the right tools to each app. It works with Claude Desktop, Cursor, Codex, Zed, VS Code, CLI tools, and other clients that follow the standard MCP config format.

Easy to begin, built to scale: one import with low friction; the same setup still fits as MCP spreads across more clients, servers, and scenarios—no product swap, no restart ritual.

Live site: mcp.umate.ai · Docs: mcp.umate.ai/docs

📑 Table of Contents

• MCPMate
  • 📑 Table of Contents
  • 🤔 Why MCPMate?
  • 🔄 How It Works
  • 🚀 Key Features
  • 🛠️ Core Components
    • Proxy
    • Bridge
    • Runtime Manager
    • Desktop App
    • Logs
  • ⚡ Quick Start
    • Option A: Download the Desktop App (Recommended)
    • Option B: Build from Source
    • Option C: Online Demo
  • 🧰 Tech Stack
  • 🚢 Deployment Modes
  • 🔧 Development
  • 🗺️ Roadmap
  • 🤝 Contributing
  • 📄 License

🤔 Why MCPMate?

Managing MCP across multiple AI tools (Claude Desktop, Cursor, Zed, Codex, and custom clients) gets messy fast:

🔄 How It Works

flowchart LR
    subgraph mgmt ["🖥️ Management"]
        APP["Tauri Desktop"]
        DASH["Web Dashboard"]
    end

    subgraph proxy ["⚙️ MCPMate Proxy"]
        direction TB
        UP["Upstream MgmtConnection Pool · OAuth 2.0 + PKCE"]
        PROF["Profile EngineScene · App · Dynamic"]
        SEC["Event Logs & SecuritySecure Store · Structured Logs · SQLite Catalog"]
        UP --> PROF --> SEC
    end

    subgraph cfg ["🔧 Client Config"]
        direction TB
        DET["Detection & Adapter"]
        MODES["ModesTransparent · Hosted · Unify"]
        DET --> MODES
    end

    subgraph clients ["📱 AI Clients"]
        C["Cursor · VS Code · Zed · ..."]
    end

    subgraph upstream ["☁️ Upstream MCP Servers"]
        S["uvx · bunx · npxSSE · Streamable HTTP"]
    end

    subgraph market ["🛒 MCP Marketplace"]
        M["Official Registry"]
    end

    APP -->|"API"| proxy
    DASH -->|"API"| proxy
    market -.->|"Install"| proxy
    upstream -->|"stdio / HTTP"| proxy
    proxy -->|"Bridge / HTTP"| cfg
    MODES --> clients

    classDef mgmt fill:#e3f2fd,stroke:#1565c0,color:#000
    classDef proxy fill:#fff3e0,stroke:#e65100,color:#000
    classDef cfg fill:#e8f5e9,stroke:#2e7d32,color:#000
    classDef clients fill:#fce4ec,stroke:#c62828,color:#000
    classDef upstream fill:#f3e5f5,stroke:#6a1b9a,color:#000
    classDef market fill:#fff9c4,stroke:#f9a825,color:#000

    class APP,DASH mgmt
    class UP,PROF,SEC proxy
    class DET,MODES cfg
    class C clients
    class S upstream
    class M market

MCPMate sits between your AI clients and MCP servers. To each app it looks like a normal MCP endpoint—no workflow disruption—while profiles, policy, and routing stay in the middle layer. The Bridge adapts stdio-only clients (such as Claude Desktop) to the HTTP proxy. The Profile Engine decides which tools each client sees—scene profiles for workflow context, app profiles for per-client tuning, and dynamic profiles that adjust at runtime. Transparent, Hosted, and Unify setup modes let you choose how much MCPMate sits in the path versus writing native client configs.

🚀 Key Features

🛠️ Core Components

Proxy

A high-performance MCP proxy server that connects to multiple MCP servers and aggregates their tools. Implements stdio and Streamable HTTP transport protocols aligned with the current MCP specification. Accepts legacy SSE-configured servers and automatically normalizes them to Streamable HTTP for backward compatibility.

Bridge

A lightweight bridging component that converts stdio protocol to HTTP transport without modifying the client. Automatically inherits all functions and tools from the HTTP service. Minimal configuration — only requires service address.

Runtime Manager

Installs and manages runtimes used by local MCP servers. Supports Node.js, uv (Python), and Bun with download progress tracking and automatic environment variable configuration.

runtime install node   # Install Node.js for JavaScript MCP servers
runtime install uv     # Install uv for Python MCP servers
runtime install bun    # Install Bun
runtime list           # List installed runtimes

Desktop App

Cross-platform desktop application built with Tauri 2. Complete graphical interface for managing MCP servers, profiles, and tools with real-time monitoring, intelligent client detection, and system tray integration. macOS, Windows, and Linux desktop builds are currently available as Beta releases.

Logs

Structured operational log for MCP proxy activity. Collects MCP operations and management-side changes into a structured timeline with cursor-based pagination, REST APIs, and a dedicated Logs page in the dashboard UI.

⚡ Quick Start

Option A: Download the Desktop App (Recommended)

Download the latest release for your platform from GitHub Releases.

> Note: macOS builds are signed and notarized to reduce system security prompts and improve package trust.

macOS and Linux users can also install the Homebrew Beta cask with `brew install --cask loocor/tap/mcpmate@beta`. See the Installation guide for updates and uninstall steps.

Option B: Build from Source

Prerequisites: Rust 1.85+, Node.js 18+ or Bun, SQLite 3

1. Clone & Build the Backend

git clone https://github.com/loocor/MCPMate.git
cd MCPMate/backend
cargo build --release

2. Start the Proxy

cargo run --release

The proxy starts with:

• REST API on `http://localhost:8080`
• MCP endpoint on `http://localhost:8000`

3. Launch the Dashboard

cd ../board
bun install
bun run dev

Dashboard available at `http://localhost:5173`.

Option C: Online Demo

Coming soon. An online environment will let you explore the dashboard, profiles, and client configuration without a local setup.

🧰 Tech Stack

🚢 Deployment Modes

• Integrated mode (desktop) — Tauri bundles backend + dashboard for local all-in-one operation
• Separated mode (core server + UI) — Run backend independently and connect either the web dashboard or desktop shell to that core service
• Client mode flexibility — Managed clients can continue using hosted/transparent workflows while the control plane runs remotely

🔧 Development

# Run all checks
./scripts/check

# Start backend + board together
./scripts/dev-all

See AGENTS.md for development guidelines, coding standards, and contribution workflow.

🗺️ Roadmap

1. Discovery-to-install polish — tighter browser extension, Market, README, and source-metadata flows

2. Account-based configuration backup & restore

3. Skills-mode packaged profiles

4. Standalone Inspector — a focused path for MCP server connection, capability discovery, and call verification

🤝 Contributing

Contributions are welcome! Please:

1. Read AGENTS.md for development guidelines

2. Open an issue to discuss significant changes

3. Submit pull requests against the `main` branch

📄 License

GNU Affero General Public License v3.0 (AGPL-3.0)