browserbase/mcp-server-browserbase
Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)
Ads
Overview
Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)
Installation
npm install && npm run build
Configuration
{
"mcpServers": {
"browserbase": {
"type": "http",
"url": "https://mcp.browserbase.com/mcp"
}
}
}Capabilities
- Start a cloud browser session
Ask your assistant to create or reuse a Browserbase session with `start`.
- Navigate to any URL
Direct the browser to a specific web page using `navigate`.
- Perform actions on a page
Instruct the assistant to click, type, or interact with elements via `act`.
- Observe interactive elements
Request a list of actionable page elements matching an instruction with `observe`.
- Extract structured data
Pull information from the current page using `extract`, optionally guided by a natural language instruction.
- End the browser session
Close the active Browserbase session cleanly with `end`.
Tags
- browser-automation
- web-scraping
- browserbase
- awesome-list
Related MCP servers
Playwright MCP
Control browsers with Playwright to navigate pages, capture snapshots, and automate flows.
Puppeteer MCP Server
OfficialAutomate headless Chrome with Puppeteer for scraping and UI verification tasks.
site-shot/site-shot-mcp
Website screenshot API for AI agents. Real Chromium rendering, full-page capture up to 20,000px, country/geo proxies, and automatic ad & cookie-banner removal (cleaner images, fewer vision tokens). Two tools: `capture_screenshot`, `capture_full_page`. Install: `npx -y site-shot-mcp`.
seleniumboot/selenium-mcp
Python MCP server for Selenium WebDriver — 84 tools for browser automation, element interactions, assertions, and self-healing locators, plus codegen for Java TestNG / JUnit 5 / Cucumber / pytest / C# NUnit / Playwright and CI pipelines (GitHub Actions / Jenkins / GitLab CI). No ChromeDriver setup needed.