agent-browser-mcp-server

agent-browser-mcp-server

Provides complete browser automation capabilities for AI agents via 44 tools, including navigation, element interaction, state management, and session recording.

Category
Visit Server

README

Agent-Browser MCP

English | 简体中文 | 日本語

Model Context Protocol (MCP) server for agent-browser - providing complete browser automation capabilities for AI agents.

This project is an independent MCP server implementation that wraps the excellent agent-browser CLI tool, making its powerful browser automation features available through the Model Context Protocol.

Features

  • 🔧 44 Tools - Complete coverage of agent-browser's functionality
  • 🎯 Token-Efficient @ref System - Reduces token usage by caching element references
  • 🌐 Full Playwright API - Leverage the complete browser automation capabilities
  • 🔄 Auto-Launch - Browser starts automatically when needed
  • 💾 State Persistence - Save and restore browser state across sessions
  • 🎬 Video Recording - Record browser sessions for debugging
  • 🌐 Network Interception - Monitor and modify network requests
  • 📊 Session Management - Manage multiple tabs and windows

Installation

Using npm

npm install agent-browser-mcp-server

From Source

git clone https://github.com/hughedward/agent_browser_mcp.git
cd agent_browser_mcp
npm install
npm run build

Quick Start

For Claude Desktop

  1. Install the package
  2. Configure in Claude Desktop settings (~/.claude/settings.json):
{
  "mcpServers": {
    "agent-browser-mcp-server": {
      "command": "npx",
      "args": ["agent-browser-mcp-server"],
      "env": {
        "HEADED": "false"
      }
    }
  }
}

Standalone

agent-browser-mcp-server

Available Tools

Core Tools

  • browser_navigate - Navigate to a URL
  • browser_snapshot - Capture page structure with @ref system
  • browser_screenshot - Take screenshots
  • browser_close - Close browser/page

Navigation & History

  • browser_back - Go back in history
  • browser_forward - Go forward in history
  • browser_reload - Reload the current page

Element Interaction

  • browser_click - Click an element
  • browser_fill - Fill input fields
  • browser_type - Type without clearing
  • browser_select - Select dropdown options
  • browser_check / browser_uncheck - Check/uncheck checkboxes
  • browser_drag - Drag and drop
  • browser_upload - Upload files
  • browser_dblclick - Double click
  • browser_focus - Focus elements
  • browser_hover - Hover over elements
  • browser_scroll - Scroll page
  • browser_press - Press keyboard keys

Element Discovery

  • browser_find - Semantic element search (role, text, label, placeholder, etc.)
  • browser_get - Get element information
  • browser_is - Check element state

Tabs & Windows

  • browser_tab - Manage tabs
  • browser_window - Manage windows
  • browser_frame - Switch to iframes

Advanced Features

  • browser_record - Record browser sessions
  • browser_network - Monitor network requests
  • browser_console - Access console
  • browser_errors - Track JavaScript errors
  • browser_trace - Performance tracing
  • browser_profiler - Chrome DevTools profiling
  • browser_evaluate - Execute JavaScript
  • browser_pdf - Export to PDF
  • browser_dialog - Handle JavaScript dialogs
  • browser_download - Manage downloads

State & Storage

  • browser_state - Save/load browser state
  • browser_cookies - Manage cookies
  • browser_storage - Access localStorage/sessionStorage

Utilities

  • browser_wait - Wait for conditions
  • browser_set - Set element attributes
  • browser_mouse - Mouse control
  • browser_diff - Compare pages
  • browser_highlight - Debug highlighting

Configuration

Environment Variables:

Variable Description Default
HEADED Run in headed mode (visible browser) false
BROWSER Browser to use (chromium/firefox/webkit) chromium

Development

# Install dependencies
npm install

# Build
npm run build

# Run in development mode (auto-rebuild)
npm run dev

# Run tests
npm test

# Watch mode
npm run test:watch

# Start server
npm start

Documentation

Related Projects

License

Apache-2.0


Note: This project is an independent implementation and is not officially affiliated with Vercel or the original agent-browser project.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured