mcpField
B
Browser MCP

Browser MCP

Local
github.com/browsermcp-comBrowser Automation42Updated 66w ago

About Browser MCP

Browser MCP is an MCP server for automating web pages through Anchor Browser’s remote browser service and Playwright. It provides structured page interaction alongside cloud sessions, proxy rotation, and browser stealth capabilities.

Key features

  1. 01Automate remote browser sessions
  2. 02Navigate, click, type, and inspect pages
  3. 03Read accessibility trees without vision models
  4. 04Manage tabs, files, dialogs, and network requests
  5. 05Run through stdio or HTTP transport

Use cases

  1. 01Automate browser-based workflows using page structure
  2. 02Run web tasks through remote browser sessions
  3. 03Inspect network requests during browser automation
  4. 04Save pages as PDFs with the PDF capability

MCP support

The server exposes browser automation tools to MCP clients, including navigation, interaction, snapshots, screenshots, JavaScript evaluation, and tab management. It can connect through stdio or an HTTP endpoint.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
MCP Logo

Browser MCP Server

A Model Context Protocol (MCP) server that provides browser automation capabilities using Anchor Browser's remote browser service with Playwright. This server enables LLMs to interact with web pages through Anchor's cloud-based browsers with built-in proxies, stealth features, and advanced capabilities.

Key Features

  • Remote Browser Execution: Uses Anchor Browser's cloud infrastructure instead of local browsers
  • Built-in Proxies: Automatic residential proxy rotation and geo-targeting
  • Stealth & Anti-Detection: Advanced browser fingerprinting and anti-bot detection
  • Fast and lightweight: Uses Playwright's accessibility tree, not pixel-based input
  • LLM-friendly: No vision models needed, operates purely on structured data
  • Deterministic tool application: Avoids ambiguity common with screenshot-based approaches

Requirements

  • Node.js 18 or newer
  • Anchor Browser API Key (Get one here)
  • VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client

Getting Started

1. Clone and Build

Since this is a custom Browser MCP server, you need to build it locally:

# Clone the repository
git clone https://github.com/anchorbrowser/anchor-mcp.git
cd anchor-mcp

# Install dependencies and build
npm install
npm run build
2. Get Your Anchor API Key
  1. Sign up at anchorbrowser.io
  2. Get your API key from the dashboard
  3. Copy your API key (starts with sk-)
3. Configure MCP Client
Cursor

Add to your ~/.cursor/mcp.json:

{
  "mcpServers": {
    "anchor-browser": {
      "command": "node",
      "args": [
        "/path/to/anchor-mcp/cli.js"
      ],
      "env": {
        "ANCHOR_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}
VS Code

Add to your MCP configuration:

{
  "mcpServers": {
    "anchor-browser": {
      "command": "node",
      "args": [
        "/path/to/anchor-mcp/cli.js"
      ],
      "env": {
        "ANCHOR_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}
Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "anchor-browser": {
      "command": "node",
      "args": [
        "/path/to/anchor-mcp/cli.js"
      ],
      "env": {
        "ANCHOR_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}
4. Restart Your MCP Client

After updating the configuration, restart your MCP client (Cursor, VS Code, etc.) to load the new server.

Configuration Options

The Browser MCP server supports only essential configuration options:

node cli.js --help
Available Options:
  • --host <host> - Host to bind server to (default: localhost, use 0.0.0.0 for all interfaces)
  • --port <port> - Port to listen on for HTTP transport (Docker/server mode)
Example with Options:
{
  "mcpServers": {
    "anchor-browser": {
      "command": "node",
      "args": [
        "/path/to/anchor-mcp/cli.js",
      ],
      "env": {
        "ANCHOR_API_KEY": "sk-your-api-key-here"
      }
    }
  }
}
HTTP Server Mode (Docker):

For Docker or headless server environments:

# Run as HTTP server
ANCHOR_API_KEY="sk-your-key" node cli.js --port 8931 --host 0.0.0.0

Then configure your MCP client to use the HTTP endpoint:

{
  "mcpServers": {
    "anchor-browser": {
      "url": "http://localhost:8931/mcp"
    }
  }
}
Why So Few Options?

Since Anchor Browser handles all the complex browser management remotely, most traditional browser options are unnecessary:

  • No browser selection - Anchor uses optimized remote browsers
  • No proxy configuration - Anchor provides built-in proxy rotation
  • No browser profile management - Handled by Anchor's infrastructure
  • No network filtering - Use Anchor's dashboard for advanced controls
  • No viewport/device options - Configure these through Anchor Browser API

This keeps the MCP server simple and focused on what matters: connecting to Anchor's remote browser service.

How It Works

  1. Browser Session Creation: When you use browser tools, the MCP server calls Anchor's API to create a remote browser session
  2. Remote Connection: Connects to the remote browser via WebSocket using Chrome DevTools Protocol (CDP)
  3. Tool Execution: All browser automation happens in Anchor's cloud infrastructure
  4. Proxy & Stealth: Automatic residential proxy rotation and advanced anti-detection features
  5. Session Management: Each session is isolated and can be viewed live via Anchor's dashboard

Benefits Over Local Browsers

🌐 Global Proxy Network
  • Automatic residential proxy rotation
  • Geo-targeting for different regions
  • No proxy configuration needed
🛡️ Advanced Stealth
  • Browser fingerprinting protection
  • Anti-bot detection bypass
  • Real browser environments
☁️ Cloud Infrastructure
  • No local browser dependencies
  • Consistent browser versions
  • Scalable execution
📊 Monitoring & Debugging
  • Live view of browser sessions
  • Session recordings and traces
  • Network request logging

Available Tools

The Browser MCP server provides all standard browser automation tools:

Core Automation
  • anchor_navigate - Navigate to URLs
  • anchor_click - Click elements
  • browser_type - Type text into inputs
  • browser_snapshot - Get page accessibility tree
  • browser_take_screenshot - Take screenshots
  • browser_evaluate - Execute JavaScript
  • browser_wait_for - Wait for conditions
Tab Management
  • browser_tab_new - Open new tabs
  • browser_tab_list - List open tabs
  • browser_tab_select - Switch between tabs
  • browser_tab_close - Close tabs
Advanced Features
  • browser_file_upload - Upload files
  • browser_handle_dialog - Handle alerts/confirms
  • browser_network_requests - View network traffic
  • browser_pdf_save - Generate PDFs (with --caps=pdf)

Troubleshooting

Invalid API Key
Error: Missing ANCHOR_API_KEY environment variable

Solution: Make sure your API key is correctly set in the MCP configuration.

Build Errors
npm run build

Solution: Make sure you have Node.js 18+ and run npm install first.

Connection Issues

Check the MCP logs for Anchor API responses and WebSocket connection status.

Session Limits

Each Anchor API key has session limits. Check your dashboard at anchorbrowser.io for usage.

Development

To modify or extend the Browser MCP server:

# Make changes to TypeScript files in src/
# Then rebuild
npm run build

# Test your changes
node cli.js --help

The server will automatically use Anchor's remote browsers for all operations, providing the benefits of cloud-based browser automation with advanced proxy and stealth capabilities.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Support

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.