Puppeteer MCP Server

Enables AI agents to automate Chrome/Chromium browser through the Model Context Protocol using Puppeteer. Supports navigating to URLs, taking screenshots, clicking elements, filling forms, and extracting page content. Useful for web scraping, testing, and automated web interactions.

Security Assessment

Level	caution
Permissions	browse:web, capture:screenshots, interact:pages
Data Exposure	content
Requires Supervisor	No
Risk Notes	Browser automation. Can navigate to URLs, take screenshots, interact with pages.

Integration

Type	`mcp-server`
Package	`@modelcontextprotocol/server-puppeteer`
Install	`npx -y @modelcontextprotocol/server-puppeteer`
Auth	none

Capabilities

Actions	navigate_to_url, take_screenshot, click_element, fill_form, extract_content, evaluate_javascript
Input Types	text, url
Output Types	text, image, json
When to Use	When the agent needs to automate browser interactions, take screenshots, or scrape dynamic web pages.
When NOT to Use	When simple HTTP fetching is sufficient; use fetch-mcp instead for static content.

Category: content · Free tier: Yes · Source

Collected: 2026-03-15 from https://github.com/modelcontextprotocol/servers/tree/main/src/puppeteer