Daemonize MCP server

Enables AI agents to manage long-running development servers by providing tools to start, monitor, stop, and debug processes like Vite or Next.js without manual terminal handling.
Back to servers
Setup instructions
Provider
mackee
Release date
May 01, 2025
Language
TypeScript
Stats
5 stars

MCP-Daemonize is a Model Context Protocol (MCP) server that enables AI agents like Claude Code and Cline to manage long-running processes, such as development servers. It solves the problem of AI agents waiting for commands to finish by providing tools to start, stop, and monitor daemons while accessing their logs in real time.

Prerequisites

  • Go 1.24.2 or later
  • (Optional) Docker for container deployment

Installation

Download from GitHub Releases

wget https://github.com/mackee/mcp-daemonize/releases/download/vX.Y.Z/mcp-daemonize_X.Y.Z_Darwin_x86_64.tar.gz
tar -xzf mcp-daemonize_X.Y.Z_Darwin_x86_64.tar.gz
sudo mv mcp-daemonize /usr/local/bin/

Build from Source

go install github.com/mackee/mcp-daemonize/cmd/mcp-daemonize@latest

Configuration

Add the following to your MCP host settings (e.g., mcp.json):

{
  "servers": {
    "daemonize": {
      "command": "/path/to/mcp-daemonize",
      "args": [],
      "env": {}
    }
  }
}

Replace /path/to/mcp-daemonize with the actual path to the binary.

Available Tools

Starting a Daemon

Use the daemonize_start tool to launch a long-running process:

{
  "name": "vite-server",
  "command": ["npm", "run", "dev"],
  "workdir": "/path/to/your/project"
}

Parameters:

  • name: Unique identifier for the daemon
  • command: Array containing the command and its arguments
  • workdir: Absolute path to the working directory

Stopping a Daemon

Use daemonize_stop to terminate a running daemon:

{
  "name": "vite-server"
}

Listing Running Daemons

Use daemonize_list to see all active daemons:

{}

Accessing Daemon Logs

Use daemonize_logs to view real-time output:

{
  "name": "vite-server",
  "tail": 50
}

Parameters:

  • name: Daemon identifier
  • tail: Number of log lines to retrieve from the end

Example Workflow

  1. Start a development server:

    {
      "name": "next-dev",
      "command": ["npx", "next", "dev"],
      "workdir": "/home/user/projects/my-next-app"
    }
    
  2. Check logs for any errors:

    {
      "name": "next-dev",
      "tail": 100
    }
    
  3. When finished, stop the server:

    {
      "name": "next-dev"
    }
    

By using these tools, AI agents can fully manage development servers, monitor their output in real-time, and perform automated debugging without requiring manual intervention.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "daemonize" '{"command":"/path/to/mcp-daemonize","args":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "daemonize": {
            "command": "/path/to/mcp-daemonize",
            "args": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "daemonize": {
            "command": "/path/to/mcp-daemonize",
            "args": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later