Ferrum
A Model Context Protocol (MCP) server that provides web automation capabilities through Ferrum, with optional BotBrowser integration for advanced anti-detection features. This enables AI agents to interact with web pages seamlessly.
What is Ferrum?
Ferrum is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that provides web automation capabilities through ferrum, with optional botbrowser integration for advanced anti-detection features. this enables ai agents to inter...
A Model Context Protocol (MCP) server that provides web automation capabilities through Ferrum, with optional BotBrowser integration for advanced anti-detection features. This enables AI agents to interact with web pages seamlessly.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that provides web auto
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ferrummcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Ferrum
FerrumMCP is a Ruby-based MCP server that gives AI agents full browser automation capabilities through the Ferrum headless Chrome library, exposing over 27 tools for session management, navigation, element interaction, content extraction, and JavaScript execution. It supports an optional BotBrowser integration for advanced anti-detection when scraping sites with bot protection, and includes AI-assisted CAPTCHA solving in experimental form. Teams use it to automate web workflows — form submission, data scraping, login flows, and screenshot capture — directly from AI assistants without writing separate automation scripts.
Prerequisites
- Ruby 3.2 or higher
- Chrome, Chromium, Edge, or Brave browser installed
- Docker (recommended for easy deployment) or bundler for source installation
- An MCP-compatible client such as Claude Desktop
- Optional: BotBrowser binary for anti-detection support
Pull and run the Docker image (recommended)
The Docker image bundles Ruby, Chrome, and all dependencies. Use --security-opt to allow the sandbox Chrome requires.
docker pull eth3rnit3/ferrum-mcp:latest
docker run --security-opt seccomp=unconfined -p 3000:3000 eth3rnit3/ferrum-mcp:latestAlternative: install the gem directly
Install the ferrum-mcp gem and start the server if you prefer a native installation over Docker.
gem install ferrum-mcp
ferrum-mcp startAlternative: build from source
Clone the repository, install gem dependencies with Bundler, and start the server manually.
git clone https://github.com/Eth3rnit3/FerrumMCP.git
cd FerrumMCP
bundle install
ruby bin/ferrum-mcpVerify the server is running
The server exposes an HTTP endpoint on port 3000. Check that it responds before connecting your MCP client.
curl http://localhost:3000/Configure Claude Desktop
Register FerrumMCP in your claude_desktop_config.json. The server runs as a persistent process; Claude Desktop connects via the SSE or stdio transport exposed on port 3000.
{
"mcpServers": {
"ferrummcp": {
"command": "ferrum-mcp",
"args": ["start"]
}
}
}Ferrum Examples
Client configuration
Claude Desktop configuration connecting to a locally running FerrumMCP gem instance.
{
"mcpServers": {
"ferrummcp": {
"command": "ferrum-mcp",
"args": ["start"]
}
}
}Prompts to try
Prompts that use FerrumMCP's browser automation tools via Claude.
- "Create a browser session, navigate to https://example.com, and take a screenshot."
- "Fill in the login form at https://myapp.com/login with username admin and submit it."
- "Search for 'MCP servers' on Google and extract the titles and URLs of the first 5 results."
- "Open the page, accept the cookie banner automatically, and extract all product prices from the table."Troubleshooting Ferrum
Chrome fails to launch with 'sandbox' or permission errors
When running Docker, always include --security-opt seccomp=unconfined. For native installs on Linux, ensure the chrome or chromium binary is in PATH and the user has permission to run it.
Sessions accumulate and memory usage grows over time
FerrumMCP automatically closes idle sessions after 30 minutes by default. You can also explicitly close a session via the close_session tool after your workflow completes.
BotBrowser anti-detection is not working
BotBrowser requires a separately downloaded binary and must be pointed to via the BROWSER_PATH or equivalent environment variable. Consult the docs/CONFIGURATION.md file in the repository for the exact variable name.
Frequently Asked Questions about Ferrum
What is Ferrum?
Ferrum is a Model Context Protocol (MCP) server that model context protocol (mcp) server that provides web automation capabilities through ferrum, with optional botbrowser integration for advanced anti-detection features. this enables ai agents to interact with web pages seamlessly. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Ferrum?
Follow the installation instructions on the Ferrum GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Ferrum?
Ferrum works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Ferrum free to use?
Yes, Ferrum is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Ferrum Alternatives — Similar Browser Automation Servers
Looking for alternatives to Ferrum? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Ferrum in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Ferrum?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.