Skip to main content
Glama

MCP Bridge Server

A macOS-native bridge server for the Model Context Protocol (MCP) that enables communication between different AI clients like Claude and Cline.

Overview

The MCP Bridge Server acts as an intermediary between different MCP clients, allowing them to communicate with each other. It provides:

  • macOS-native integration with launchd service and Unix domain sockets

  • Persistent client registration across restarts

  • Seamless communication between different AI clients

  • Tool routing between clients

Related MCP server: ACP-MCP-Server

Project Status

This project is under active development. Current status:

  • Basic bridge server implementation

  • Unix socket transport layer

  • macOS service integration framework

  • Robust connection handling and error recovery

  • Enhanced logging for debugging

  • Complete LaunchAgent configuration

  • Service lifecycle management

  • Client persistence implementation

  • Recovery mechanisms for service restarts

  • Client discovery and registration protocol

  • Configuration templates for Claude and Cline

Architecture

The MCP Bridge Server consists of several key components:

  1. BridgeServer: Core server implementation that handles client connections and message routing

  2. UnixSocketTransport: macOS-native transport layer using Unix domain sockets

  3. StateManager: Manages client state and persistence

  4. MacOSServiceManager: Handles integration with macOS launchd service

Installation

Coming soon

Usage

Coming soon

Development

Prerequisites

  • Node.js 18+

  • TypeScript

  • macOS (for native features)

Building

# Install dependencies
npm install

# Build the project
npm run build

# Start the server
npm start

Testing

# Run tests
npm test

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

Available Tools

2 tools
discover_clientC

Find and optionally start an MCP client

Inputs: clientType (required), autoStart, timeout.

tools/callC

Execute a tool on a remote MCP client

Inputs: method (required), arguments (required), targetType.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: discover_client is for finding/starting clients, while tools/call is for executing tools on those clients. There is no overlap or ambiguity between these functions, making them easy to differentiate.

    Naming Consistency3/5

    The naming is mixed: discover_client uses snake_case with a verb-noun pattern, while tools/call uses a path-like structure (noun/verb). This inconsistency in convention reduces predictability, though both names are still readable and descriptive.

    Tool Count4/5

    With only 2 tools, the count is minimal but appropriate for a bridge server's core functions of discovering clients and calling their tools. It feels slightly thin but covers essential operations without unnecessary bloat.

    Completeness4/5

    For a bridge server, the tools cover the key workflows: discovering clients and executing tools on them. A minor gap might be the lack of a tool for managing client connections (e.g., disconnecting), but the core functionality is well-covered.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      F
      maintenance
      A bridge server that connects Agent Communication Protocol (ACP) agents with Model Context Protocol (MCP) clients, enabling seamless integration between ACP-based AI agents and MCP-compatible tools like Claude Desktop.
      16
      81 PyPI
      24
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that allows AI assistants to communicate with the ChatGPT desktop app on macOS, enabling users to send prompts to ChatGPT from any MCP-compatible assistant.
      3
      89 PyPI
      81
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that enables AI assistants to communicate with each other using Inter-Process Communication, featuring natural language commands and cross-platform compatibility.
      9
      132
      MIT