MCP Installer

What is mcp-installer

mcp-installer is a specialized server tool developed by anaisbetts designed to streamline the installation of other MCP (Model Context Protocol) servers. It acts as a convenient intermediary that allows users to leverage the capabilities of Claude, an AI assistant, to install MCP servers hosted on npm or PyPi with ease. This server is particularly useful for users looking to quickly set up various MCP servers without manually handling installation processes. It requires the installation of npx for node servers and uv for Python servers to function effectively.

How to Use mcp-installer

To use the mcp-installer, you'll need to configure it within your Claude desktop configuration. Here's a step-by-step guide:

1. Configuration: Modify your claude_desktop_config.json file located at either ~/Library/Application Support/Claude on macOS or C:\Users\NAME\AppData\Roaming\Claude on Windows. Add the following snippet to the configuration:

   "mcpServers": {
     "mcp-installer": {
       "command": "npx",
       "args": [
         "@anaisbetts/mcp-installer"
       ]
     }
   }
   

2. Prompt Claude: Once configured, you can instruct Claude to install MCP servers for you. Here are some example prompts:

   • "Hey Claude, install the MCP server named mcp-server-fetch."
   • "Hey Claude, install the @modelcontextprotocol/server-filesystem package as an MCP server. Use ['/Users/anibetts/Desktop'] for the arguments."
   • "Hi Claude, please install the MCP server at /Users/anibetts/code/mcp-youtube, I'm too lazy to do it myself."
   • "Install the server @modelcontextprotocol/server-github. Set the environment variable GITHUB_PERSONAL_ACCESS_TOKEN to '1234567890'."

These prompts highlight the flexibility of mcp-installer, allowing for both package installations and specific configurations such as setting environment variables.

Key Features of mcp-installer

• Automated Installations: The primary function of mcp-installer is to automate the installation of MCP servers, saving users time and effort.

• Integration with Claude: By integrating with Claude, users can simply instruct the AI to handle installations, making the process accessible even to those with limited technical knowledge.

• Support for npm and PyPi: mcp-installer can handle packages hosted on both npm and PyPi, offering a wide range of server options for different use cases.

• Environment Configuration: Users can specify arguments and environment variables during installation, providing flexibility and control over the setup process.

• User-Friendly Setup: The configuration process involves minimal setup changes, making it easy for users to get started quickly.

Overall, mcp-installer is a powerful tool for anyone looking to simplify the deployment of MCP servers, providing an efficient and user-friendly interface for managing server installations through AI assistance.