MCP server ingerate with vercel-labs's Agent Browser
概览
A Model Context Protocol (MCP) server that provides browser automation capabilities through Vercel's agent-browser. This enables LLMs to interact with web pages using a fast Rust CLI with Node.js fallback. Then use tools like browser_navigate, browser_click, browser_snapshot to control the browser from your AI agent. - - Semantic element locators using accessibility properties, text matching, and data attributes - - Multiple isolated browser sessions with separate cookies, storage, and navigation history - - Navigation, form filling, clicking, scrolling, keyboard input, and more - - Get text, HTML, attributes, accessibility snapshots, screenshots, and PDFs - - Full control over browser cookies and storage - - Run arbitrary scripts in the browser context - - Monitor console messages and network requests - - Extract structured data from websites for RAG, research, or analysis - - AI-powered end-to-end testing with natural language assertions - - Fill forms, submit data, handle...
README
以下为原文 README 节选，完整内容请查看原文。
Agent Browser MCP
A Model Context Protocol (MCP) server that provides browser automation capabilities through Vercel’s agent-browser. This enables LLMs to interact with web pages using a fast Rust CLI with Node.js fallback.
Quick Start
# 1. Install agent-browser CLI
npm install -g agent-browser && agent-browser install
# 2. Add to Claude Desktop (or your MCP client)
npx agent-browser-mcp
Then use tools like browser_navigate, browser_click, browser_snapshot to control the browser from your AI agent.
Features
- AI-Optimized Browser Control - Semantic element locators using accessibility properties, text matching, and data attributes
- Session Isolation - Multiple isolated browser sessions with separate cookies, storage, and navigation history
- Comprehensive Automation - Navigation, form filling, clicking, scrolling, keyboard input, and more
- Data Extraction - Get text, HTML, attributes, accessibility snapshots, screenshots, and PDFs
- Cookie Management - Full control over browser cookies and storage
- JavaScript Execution - Run arbitrary scripts in the browser context
- Network Inspection - Monitor console messages and network requests
Use Cases
- Web Scraping for AI - Extract structured data from websites for RAG, research, or analysis
- Automated Testing - AI-powered end-to-end testing with natural language assertions
- Form Automation - Fill forms, submit data, handle multi-step workflows
- Screenshot Analysis - Capture pages for visual AI analysis or documentation
- Session Automation - Login once, persist cookies, automate authenticated workflows
- Data Entry - Bulk data input across web applications
- Monitoring - Track changes on web pages, detect updates, gather metrics
Why Agent Browser?
Agent Browser was built from the ground up for AI agents, not adapted from human-centric automation tools. This fundamental difference delivers significant advantages:
Agent-Native Design
| Capability | Agent Browser | Traditional Tools |
|---|---|---|
| Semantic Element Targeting | Native accessibility-based locators | CSS selectors / XPath |
| Token Efficiency | Structured data, minimal output | Verbose HTML/screenshots |
| Response Format | AI-optimized, parseable | Human-readable |
| Error Messages | Actionable, context-aware | Generic stack traces |
Performance
- Rust-powered CLI - Fast execution with minimal overhead
安装
npx agent-browser-mcp配置
{
"mcpServers": {
"agent-browser": {
"command": "npx",
"args": ["agent-browser-mcp"]
}
}
}