Browser-use-claude-mcp
by jasondsmith72
A browser automation MCP server for AI models like Claude and Gemini 2.5, enabling web browsing capabilities through natural language. It allows AI assistants to browse the web, interact with websites, and extract information using natural language commands.
Last updated: N/A
What is Browser-use-claude-mcp?
This project implements a Model Context Protocol (MCP) server that provides browser automation capabilities to AI models. It allows AI assistants to browse the web, interact with websites, and extract information using natural language commands.
How to use Browser-use-claude-mcp?
To use this server, clone the repository, install dependencies, configure environment variables, build the project, and start the server. Then, configure your AI model (e.g., Claude Desktop) to use this MCP server by adding it to the configuration file.
Key features of Browser-use-claude-mcp
Full browser automation (navigation, form filling, clicking, etc.)
Web search capabilities
Screenshot capture for visual understanding
Content extraction and analysis
Support for multiple AI providers (Google Gemini 2.5, Anthropic Claude, OpenAI)
Image analysis (vision) capabilities
AI-powered content analysis
Written in TypeScript for maximum reliability
Modular architecture with clean separation of concerns
Comprehensive logging and error handling
Easy configuration through environment variables
Use cases of Browser-use-claude-mcp
Enabling AI assistants to browse the web and answer questions based on web content.
Automating form filling and data extraction from websites.
Providing AI models with visual context through screenshot analysis.
Integrating web search capabilities into AI workflows.
FAQ from Browser-use-claude-mcp
What AI models are supported?
What AI models are supported?
Currently, the server primarily focuses on Google Gemini 2.5, but also supports Anthropic Claude and OpenAI.
How do I configure the server?
How do I configure the server?
The server is configured through environment variables in the .env file. You can set API keys, browser paths, and other settings there.
How do I integrate this with Claude Desktop?
How do I integrate this with Claude Desktop?
You need to modify the claude_desktop_config.json file to include this MCP server in the mcpServers section.
What tools are available?
What tools are available?
Available tools include browse_webpage, search_web, take_screenshot, click_element, fill_form, extract_content, and analyze_content.
What is MCP?
What is MCP?
MCP stands for Model Context Protocol. It's a protocol that allows AI models to interact with external tools and services, such as a browser.