mcp-browser-use: MCP server for browser-use
@vinayak-mehta
关于 mcp-browser-use: MCP server for browser-use
MCP server for browser-use
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-browser-use": {
"command": "uvx",
"args": [
"mcp-browser-use"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is mcp-browser-use?
mcp-browser-use is an MCP server that connects any MCP client (such as Claude or Cursor) to the browser using the browser-use library. It is designed for users who want to control a browser through their existing MCP client without needing a separate LLM API key.
How to use mcp-browser-use?
Run the command uvx mcp-browser-use in your MCP client’s configuration. Provide the full path to uvx if your MCP client fails to start the server.
Key features of mcp-browser-use
- Connects any MCP client to the browser via browser-use.
- Uses the LLM already configured in your MCP client.
- No need for a separate, paid LLM API key.
- Easy to start with a single uvx command.
Use cases of mcp-browser-use
- Control a browser from an AI assistant (e.g., Claude, Cursor) through MCP.
- Automate browser-based tasks using natural language instructions.
FAQ from mcp-browser-use
What MCP clients does it work with?
It works with any MCP client, such as Claude or Cursor.
Do I need a separate LLM API key to use this server?
No. Unlike other browser-use MCPs, this server uses the LLM already set up in your MCP client.
How do I start the server?
Place the command uvx mcp-browser-use in your MCP client’s configuration. Ensure the full path to uvx is provided if the client fails to start the server.
浏览器自动化 分类下的更多 MCP 服务器
playwright-server MCP server
blackwhite084Scrapling Fetch MCP
cyberchittaHelps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.
Browser Control MCP
eyalzhMCP server paired with a browser extension that enables AI agents to control the user's browser.
Fastcrw
usFast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

Fetch
modelcontextprotocolModel Context Protocol Servers
评论