ClaudeMap

Puppeteer MCP Server

Reference MCP server for browser automation via Puppeteer.

MCP Serversofficialpuppeteerbrowserreferencearchived

Provides Claude with the ability to launch a headless browser, navigate pages, fill forms, click elements, screenshot, and execute JavaScript.

What it does

  • Browser automation tools: navigate, click, hover, fill, select, evaluate, screenshot
  • Console logs exposed as `console://logs` resource; screenshots as `screenshot://<name>`
  • npx `@modelcontextprotocol/server-puppeteer`; PUPPETEER_LAUNCH_OPTIONS env or per-call launchOptions

When to use it

When Claude needs a real browser: scrape a JS-rendered page, drive a UI flow, take screenshots for visual verification. For heavier automation look at Playwright-based community servers.

Getting started

Add to .mcp.json under mcpServers.puppeteer:

{
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-puppeteer"]
}

Docker (headless chromium): `{"command": "docker", "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]}`.

Things to know

Archived reference implementation. Real security surface: it runs a browser that can hit local files and internal IPs — README carries an explicit caution. npx mode opens a visible browser window; only the Docker image is headless.

Repository

modelcontextprotocol/servers-archived

Charted

Related on the map

  • Blitz Strike

    MCP Server

    A penetration-testing methodology delivered as one MCP server: BLITZ maps the attack surface, EAGLE-EYE traces source-to-sink, STRIKE live-verifies every finding before it is reported.

    • mcp-server
    • security
    • pentest
    • methodology
  • Ripwire

    MCP Server

    Red Hat's "ripgrep for AI context" — a C++23 zero-dependency CLI that also speaks MCP.

    • mcp
    • code-context
    • cli
    • red-hat
  • Deja Vu

    MCP Server

    One shared session memory for 25+ coding agents — Claude Code, Codex, and Cursor finally remember the same project.

    • mcp
    • memory
    • cross-agent
    • context