mcp-linker

mcp store manager, add & syncs MCP server configurations across clients like Claude code, Cursor💡 build-in Codex agent use ChatGPT subscription, mcphub

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio milisp-mcp-linker docker run -i milisp/mcp-linker:latest \
  --env MCP_LINKER_LOG_LEVEL="INFO" \
  --env MCP_LINKER_SYNC_ENABLED="true"

How to use

MCP Linker is a desktop application that connects your AI clients to a built-in marketplace of MCP servers and configurations. It provides a centralized GUI to browse, preview, and install MCP server configurations to supported clients, enabling you to drop in new capabilities without direct LLM calls. The app detects your environment (Python, Node.js, uv/virtual environments) and lets you push selected MCP servers to your target clients with a few clicks. Use the Marketplace to explore 600+ curated MCP servers, then use the Add or Get actions to install and apply the server configuration to your chosen AI client, such as Codex CLI-based workflows, VS Code integrations, or other desktop clients supported by MCP Linker.

How to install

Prerequisites:

A supported desktop OS (macOS, Windows, or Linux).
Optional: Docker installed if you plan to run the provided Docker image; otherwise use the direct download installer.

Installation options:

macOS (Homebrew) or Windows/Linux (Direct Download):
- Visit the MCP Linker releases page and download the latest installer or package for your OS.
- Run the installer and follow on-screen prompts to complete installation.
Docker (advanced / portable usage):
- Ensure Docker is installed and running.
- Pull and run the MCP Linker image: docker pull milisp/mcp-linker:latest docker run -it milisp/mcp-linker:latest
First run:
- Launch the application from your start menu / Applications folder or from the Docker container.
- Sign in if required and allow the app to detect your AI clients and environments (Python, Node.js, uv).
- Open the Marketplace, browse MCP servers, and click Get to view configuration details. Use Add to install to your selected client and start leveraging the new capabilities immediately.

Additional notes

Tips and common issues:

Ensure your AI clients (e.g., Codex CLI, VS Code, or other supported apps) are installed and accessible on your system before adding MCP servers.
If you encounter environment-detection issues, verify that Python, Node.js, or uv environments are properly installed and available on your PATH.
Some MCP servers require a paid plan for cloud sync features; verify your subscription status in the Pro plan section of MCP Linker.
If the marketplace shows network errors, check your internet connection or retry after signing in to your account.
For developers, contributions are welcome via the CONTRIBUTING guide; issue templates and discussions are available in the repository.

Related MCP Servers

basic-memory

2.6k

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

tuui

1.1k

A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

openapi

123

OpenAPI definitions, converters and LLM function calling schema composer.

apple-mail

MCP server giving AI assistants full access to Apple Mail - read, search, compose, organize & analyze emails via natural language

macOS-Notification

macOS Notification MCP enables AI assistants to trigger native macOS sounds, visual notifications, and text-to-speech. Built for Claude and other AI models using the Model Context Protocol.

gtm

An MCP server for Google Tag Manager. Connect it to your LLM, authenticate once, and start managing GTM through natural language.