mcpField
M
MCP-DevTools

MCP-DevTools

Local
github.com/RingoTCBrowser Automation0Updated 86w ago
Repository

About MCP-DevTools

MCP-DevTools is a Puppeteer-based MCP server for browser automation and DevTools access, aimed at Cursor users. It runs in Docker and includes non-root execution and Chromium sandboxing.

Key features

  1. 01Puppeteer browser automation
  2. 02DevTools Protocol integration
  3. 03Docker-based setup
  4. 04Non-root execution
  5. 05Chromium sandboxing

Use cases

  1. 01Automating browser tasks in Cursor
  2. 02Inspecting browser behavior through DevTools
  3. 03Running browser automation in a Docker environment

MCP support

It exposes Puppeteer browser automation and DevTools capabilities to MCP clients.

#browser-automation#devtools#puppeteer

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "MCP-pptr": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "build"
      ]
    }
  }
}
Run commanddocker run -i --rm build

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocibuild

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP-DevTools

A Model Context Protocol (MCP) server implementation for enhanced browser automation and DevTools capabilities using Puppeteer.

Features

  • Full browser automation support via Puppeteer
  • Enhanced DevTools Protocol integration
  • Docker support for consistent environments
  • Non-root user execution for security
  • Cross-platform compatibility

Prerequisites

  • Docker
  • Cursor IDE

Setup

  1. Build the Docker image:
docker build -t mcp/puppeteer .
  1. Configure in Cursor:
    • Open Cursor Settings
    • Navigate to MCP Configuration
    • Add the following command:
docker run -i --rm --init -e DOCKER_CONTAINER=true mcp/puppeteer

Configuration

The server is configured to run on port 3000 by default. Environment variables:

  • PUPPETEER_EXECUTABLE_PATH: Path to Chromium executable
  • DISPLAY: X11 display for headless mode
  • CHROME_BIN: Chrome binary path

Security

  • Runs as non-root user in Docker
  • Uses Chromium's sandbox
  • Implements proper permission handling

License

MIT License

Contributing

  1. Fork the repository
  2. Create your feature branch
  3. Commit your changes
  4. Push to the branch
  5. Create a new Pull Request

Comments

Markdown supported

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.