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.
claude mcp add --transport stdio coder-ka-procm-mcp uvx procm-mcp