MCP server for safe, detection-resistant browser automation
Most browser automation work still happens through a UI a human drives. Puppeteer Real Browser MCP server moves it into the conversation instead. MCP server for safe, detection-resistant browser automation.
Give an MCP-compatible AI assistant a local Chrome browser that it can open, navigate, read, and control.
Installation goes through your MCP client rather than a global install: point it at puppeteer-real-browser-mcp-server on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
The server publishes 12 tools. What each one is for:
browser_init — Start or reuse the managed Chrome sessionnavigate — Open a URLget_content — Read full-page or selected HTML/textfind_selector — Find a CSS selector from element textclick — Click an elementtype — Clear and type into an inputwait — Wait for a selector, navigation, or timerandom_scroll — Scroll with varied timing and distancesolve_captcha — Return a placeholder attempt resultsave_content_as_markdown — Save as .md; currently blockedbrowser_close — Close the managed browser and reset workflow stateCursor — Create .cursor/mcp.json in one project, or ~/.cursor/mcp.json for all projects:Configuration is passed through the environment: CHROME_PATH, PUPPETEER_EXECUTABLE_PATH, PROXY_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
npx (included with the normal Node.js installer) - Google Chrome or Chromium - An MCP client that can start a local stdio server Claude Desktop is available on macOS and Windows. Other MCP clients can use this server on Linux.Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Puppeteer Real Browser's toolset — browser_init, navigate, get_content and 9 more — is a fair guide to whether it matches your workflow. It is maintained by withLinda; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Puppeteer Real Browser's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| browser_init | Start or reuse the managed Chrome session |
| navigate | Open a URL |
| get_content | Read full-page or selected HTML/text |
| find_selector | Find a CSS selector from element text |
| click | Click an element |
| type | Clear and type into an input |
| wait | Wait for a selector, navigation, or time |
| random_scroll | Scroll with varied timing and distance |
| solve_captcha | Return a placeholder attempt result |
| save_content_as_markdown | Save as .md; currently blocked |
| browser_close | Close the managed browser and reset workflow state |
| Cursor | Create .cursor/mcp.json in one project, or ~/.cursor/mcp.json for all projects: |
{
"mcpServers": {
"puppeteer-real-browser": {
"command": "npx",
"args": [
"-y",
"puppeteer-real-browser-mcp-server@latest"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
npx (included with the normal Node.js installer) - Google Chrome or Chromium - An MCP client that can start a local stdio server Claude Desktop is available on macOS and Windows. Other MCP clients can use this server on Linux.| Variable | Description | Required |
|---|---|---|
| CHROME_PATH | Filesystem location the server is allowed to use. | Optional |
| PUPPETEER_EXECUTABLE_PATH | Filesystem location the server is allowed to use. | Optional |
| PROXY_URL | Endpoint or connection string the server talks to. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.