Puppeteer MCP
MCP server for browser automation via Puppeteer
pptr-mcp
MCP server for browser automation via Puppeteer. Unlike other browser MCPs that expose fixed tools (navigate, click, screenshot), this server executes arbitrary JavaScript code with direct access to the Puppeteer Browser instance.
Key Difference
Most browser MCP servers provide a limited set of predefined actions. This approach requires multiple round-trips for complex workflows and can't handle edge cases.
pptr-mcp takes a different approach: it exposes a single execute tool that runs your JavaScript code in a Node.js VM with a browser global. You write Puppeteer code directly, getting full API access in one call.
Traditional MCP (5 round-trips) pptr-mcp (1 round-trip)
================================ ================================
Agent Server Agent Server
| | | |
|-- navigate --->| |-- execute ---->|
|<-- ok ---------| | |
| | | +------------------------+
|-- waitFor ---->| | | const page = await |
|<-- ok ---------| | | browser.newPage(); |
| | | | await page.goto(url); |
|-- click ------>| | | await page.click(s); |
|<-- ok ---------| | | await page.type(i, t); |
| | | | return await |
|-- type ------->| | | page.screenshot(); |
|<-- ok ---------| | +------------------------+
| | | |
|-- screenshot ->| |<-- result -----|
|<-- image ------| | |
| | | |
Requirements
- Node.js >= 20
Installation
npm install -g pptr-mcp
MCP Configuration
Add to your MCP client config (e.g., Claude Desktop):
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["pptr-mcp"]
}
}
}
With CLI options:
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["pptr-mcp", "--no-headless", "--viewport=1080p"]
}
}
}
With custom Chrome flags (after --):
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": [
"pptr-mcp",
"--viewport=1280x720",
"--",
"--proxy-server=http://proxy:8080"
]
}
}
}
CLI Options
| Option | Description |
|---|---|
--no-headless | Run with visible browser window |
--viewport=VALUE | Set viewport size (e.g., 1920x1080 or 1080p) |
--help, -h | Show help |
-- [args] | Pass remaining args to Chrome |
Unknown options before -- are also passed to Chrome.
Claude Code Plugin
Install as a Claude Code plugin:
/plugin marketplace add iatsiuk/pptr-mcp
/plugin install pptr-mcp@pptr-mcp
Environment Variables
| Variable | Description |
|---|---|
CHROME_PATH | Path to Chrome executable |
PUPPETEER_EXECUTABLE_PATH | Alternative to CHROME_PATH |
PUPPETEER_CACHE_DIR | Browser download cache directory |
PPTR_MCP_TIMEOUT | Execution timeout in ms (default: 30000) |
Tool: execute
Executes JavaScript code with access to Puppeteer browser.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
code | string | required | JavaScript code to execute |
persistent | boolean | true | Reuse browser session across calls |
Recipes
Disable headless mode
Show browser window during execution:
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["pptr-mcp", "--no-headless"]
}
}
}
Custom Chrome profile directory
Use your own Chrome profile with saved logins and cookies:
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["pptr-mcp", "--", "--user-data-dir=/path/to/profile"]
}
}
}
Use system Chrome instead of downloaded
By default, pptr-mcp downloads Chrome for Testing - a version optimized and tested for the bundled Puppeteer. To use your system Chrome instead:
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["pptr-mcp"],
"env": {
"CHROME_PATH": "/path/to/chrome"
}
}
}
}
Security
This server is designed for trusted local development with LLM assistants (Claude Code, Cursor, etc.). The executing code comes from the LLM at your request.
What this means
- Not a sandbox: The Node.js VM isolates code for convenience, not security. It is not designed to run untrusted code.
- Full browser control: Executed code can navigate to any URL, read page content, take screenshots, and interact with web applications.
- Chrome runs without sandbox:
--no-sandboxflag is used for Docker/container compatibility. - Persistent sessions: With
persistent: true(default), cookies and browser state are preserved across calls. Usepersistent: falsefor isolation.
Not designed for
- Multi-tenant or shared server deployments
- Executing untrusted code from external sources
- Building web services that accept arbitrary user input
License
相關伺服器
Scout Monitoring MCP
贊助Put performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
贊助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MagicPod
A server for integrating with MagicPod, an AI-powered test automation platform.
MCP RAG Server
A Python server providing Retrieval-Augmented Generation (RAG) functionality. It indexes various document formats and requires a PostgreSQL database with pgvector.
Sherlog MCP Server
A persistent IPython workspace for data analysis, log processing, and multi-agent collaboration.
EOL MCP Server
Check software end-of-life (EOL) dates and support status using the endoflife.date API to provide accurate lifecycle and security information.
CLI MCP Server
A secure MCP server for executing controlled command-line operations with comprehensive security features.
Remote MCP Server Authless
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Mobile Xray MCP
Take screenshots and analyze mobile apps with AI assistance directly from your IDE.
Symphony of One
An MCP server for orchestrating multiple Claude instances to collaborate in a shared workspace with real-time communication.
Model Context Protocol servers
A collection of reference implementations for the Model Context Protocol (MCP), showcasing servers implemented with TypeScript and Python SDKs.
Gateway MCP Server
A gateway server that intelligently routes MCP requests to multiple backend servers based on external configuration.