About MCPM
MCPM is a command-line tool for managing MCPs on a machine, aimed at people maintaining local servers. It lists available and running MCPs and supports pulling, stopping, and removing servers.
Key features
- 01List available local MCPs
- 02Show the currently running MCP
- 03Stop a running server
- 04Pull a specified MCP server
- 05Remove a specified MCP server
Use cases
- 01Check which MCP servers are available locally
- 02Confirm which MCP is running
- 03Stop a server that is no longer needed
- 04Pull or remove a particular server
MCP support
MCPM manages local MCP servers from the command line, including listing, checking status, stopping, pulling, and removing them.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCPM
MCPM is a command-line application for managing Model Context Protocols (MCPs) on your machine. This tool allows you to easily list available MCPs, check which one is currently running, stop a running server, pull a server, and remove a server.
Features
- List all available MCPs on the machine.
- Display the currently running MCP.
- Stop a running MCP server.
- Pull a specified MCP server.
- Remove a specified MCP server.
Installation
You can install MCPM using pip. Run the following command:
pip install mcpm
Usage
After installation, you can use the following commands:
-
List available MCPs:
mcpm list -
Show running MCP:
mcpm running -
Stop running MCP:
mcpm stop -
Pull MCP:
mcpm pull <mcp_name> -
Remove MCP:
mcpm remove <mcp_name>
Contributing
If you would like to contribute to MCPM, please fork the repository and submit a pull request.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.