Claude MarketplacesSubmit

Procm

coder-ka/procm-mcp

This server lets Claude start and manage long-running processes like dev servers, Docker Compose stacks, or test watchers, then check their stdout and stderr to debug issues autonomously. It uses a whitelist pattern for security: the LLM must ask permission once to allow a specific command in a specific directory, then can restart or monitor that process freely without repeated confirmations. Tools include start-process, delete-process, restart-process, and log retrieval commands. Processes clean up automatically when your Claude session ends. Reach for this when you want Claude to spin up services, run watchers, and iterate on fixes based on their output without manual intervention.

GitHub stars: 3
tools: 8
transport: STDIO
last updated: May 31, 2026

Tools

8 tools

Public tool metadata for what this MCP can expose to an agent.

allow-start-processAllow specific processes to be created

Allow specific processes to be created

No parameter schema in public metadata yet.

start-processStart a new process with specified script and arguments

Start a new process with specified script and arguments

No parameter schema in public metadata yet.

delete-processStop and remove a process by ID.The default signal is SIGTERM, but SIGKILL(force killing) will be sent after 10 seconds unless the process exits.

Stop and remove a process by ID.The default signal is SIGTERM, but SIGKILL(force killing) will be sent after 10 seconds unless the process exits.

No parameter schema in public metadata yet.

restart-processRestart an existing process by ID

Restart an existing process by ID

No parameter schema in public metadata yet.

get-process-infoGet detailed information about a process

Get detailed information about a process

No parameter schema in public metadata yet.

list-processesList all currently managed processes

List all currently managed processes

No parameter schema in public metadata yet.

get-process-stdoutRetrieve stdout logs from a process

Retrieve stdout logs from a process

No parameter schema in public metadata yet.

get-process-stderrRetrieve stderr logs from a process

Retrieve stderr logs from a process

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Readme

procm-mcp

A Model Context Protocol (MCP) server for process management.

Supported features

Secure and automatable process creation
Cleanup created processes automatically on termination (e.g. exiting claude code)
Common process management features supported, restarting, deleting, checking status or retreving stdout/stderr of processes

Using these features, LLMs start processes like development servers, docker-compose, or test watchers and check their outputs to fix bugs automatically.

Installation

npm i -D procm-mcp

.mcp.json

{
  "mcpServers": {
    "procm-mcp": {
      "command": "node",
      "args": ["./node_modules/procm-mcp/build/index.js"],
      "env": {}
    }
  }
}

Secure process creation

You can permit LLMs to use start-process tool without confirmation, because procm-mcp only allow whitelisted process creations.

LLMs will ask you to use allow-start-process tool to add specific process creation to the whitelist.

Once you allow a process creation, you don't have to confirming it anymore as long as the command and the working directory are the same.

View the full README on GitHub

Details

Repository: github.com/coder-ka/procm-mcp
Package: procm-mcp
Transport: STDIO
Registry: MCP registry, active