Overview
What is mcpm.sh
mcpm.sh is a command-line interface (CLI) tool designed for managing Model Context Protocol (MCP) servers across various MCP clients, similar to Homebrew.
How to Use
To use mcpm.sh, install it via a package manager or directly from the source. Use commands like 'mcpm add SERVER_NAME' to add servers, 'mcpm list' to view installed servers, and 'mcpm client' to manage active MCP clients.
Key Features
Key features of mcpm.sh include easy installation of MCP servers, centralized management of server configurations, seamless updates, server-side management capabilities, and a registry of available MCP servers.
Where to Use
mcpm.sh can be used in software development environments, particularly for teams working with multiple MCP clients and needing efficient server management.
Use Cases
Use cases for mcpm.sh include adding and managing MCP servers for different clients, switching between active clients, and temporarily disabling servers without complete removal.
Usage
Installation
Generate your exclusive SSE URL:
MCP Server Configuration (for all clients):
Installation in Cursor
Click on the Cursor settings icon in the top right, find the MCP option, then click the + button in the top right of that page and add the configuration in the config panel.
Note: Do not delete previously added configuration items
After completion, restart Cursor, chat with Cursor, and you can use MCP functions
Installation in Claude
Find this json file at the following path: macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json If this file doesn't exist, create one and paste the content above into the file.
Note: Do not delete previously added configuration items.
After completion, restart Claude, and you can use MCP functions through the Claude dialog
SDK
Installation in Python
Install composio-toolset by running the following commands in your terminal:
pip install composio_openai
Python example code:
from composio_openai import ComposioToolSet, App
from openai import OpenAI
openai_client = OpenAI()
composio_toolset = ComposioToolSet(entity_id="default")
tools = composio_toolset.get_tools(apps=[App.GITHUB])
Installation in TypeScript
Install composio-core by running the following commands in your terminal:
npm install -g composio_core
TypeScript example code:
import { OpenAI } from "openai";
import { OpenAIToolSet } from "composio-core";
const openaiClient = new OpenAI();
const composioToolset = new OpenAIToolSet();
const tools = await composioToolset.getTools({
apps: ["github"],
});