Puppeteer
The Puppeteer MCP Server provides browser automation capabilities through Puppeteer, enabling interaction with both new browser instances and existing Chrome windows to perform tasks like navigating web pages, taking screenshots, clicking elements, filling forms, and executing JavaScript. It offers intelligent Chrome tab management that can connect to active Chrome tabs while preserving existing instances, solving the problem of seamless browser automation integration within AI applications. The server is installed as a global npm package or run directly via npx, then configured in Claude Desktop or VSCode to expose Puppeteer's automation tools to language models.
- GitHub stars
- 449
- tools
- 8
- last updated
- Mar 8, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
puppeteer_connect_active_tabConnect to an existing Chrome instance with remote debugging enabled.
Connect to an existing Chrome instance with remote debugging enabled.
No parameter schema in public metadata yet.
puppeteer_navigateNavigate to a URL.
Navigate to a URL.
No parameter schema in public metadata yet.
puppeteer_screenshotTake a screenshot of the current page or a specific element.
Take a screenshot of the current page or a specific element.
No parameter schema in public metadata yet.
puppeteer_clickClick an element on the page.
Click an element on the page.
No parameter schema in public metadata yet.
puppeteer_fillFill out an input field.
Fill out an input field.
No parameter schema in public metadata yet.
puppeteer_selectUse dropdown menus.
Use dropdown menus.
No parameter schema in public metadata yet.
puppeteer_hoverHover over elements.
Hover over elements.
No parameter schema in public metadata yet.
puppeteer_evaluateExecute JavaScript in the browser console.
Execute JavaScript in the browser console.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Puppeteer MCP Server
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
Acknowledgment
This project is an experimental implementation inspired by @modelcontextprotocol/server-puppeteer. While it shares similar goals and concepts, it explores alternative approaches to browser automation through the Model Context Protocol.
Features
- Navigate web pages
- Take screenshots
- Click elements
- Fill forms
- Select options
- Hover elements
- Execute JavaScript
- Smart Chrome tab management:
- Connect to active Chrome tabs
- Preserve existing Chrome instances
- Intelligent connection handling
Project Structure
Details
Related Web & Browser Automation MCP servers
View all
Sendblue Browser Mcpsendblue-api/sendblue-browser-useDrive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.0stars
Browsersaik0s/mcp-browser-useProvides a browser automation MCP server that lets AI assistants control a real browser for navigation, form interaction, data extraction, and more.933stars
Browser Gatewaybrowser-gateway/browser-gatewayAI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.19stars
Chromehangwin/mcp-chromeChrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, e11.6Kstars
Browserbasehq Mcp Browserbasebrowserbase/mcp-server-browserbaseProvides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…3.4KstarsMcp Server Browserbasebrowserbase/mcp-server-browserbaseMCP server for AI web browser automation using Browserbase and Stagehand3.4Kstars