mcp-browser-use: MCP server for browser-use
LocalAbout mcp-browser-use: MCP server for browser-use
mcp-browser-use is an MCP server for browser-use that connects MCP clients such as Claude or Cursor to a browser. It uses the LLM already configured in the client rather than requiring a separate LLM API key. It is started with a single uvx command.
Key features
- 01Exposes browser-use capabilities to MCP clients
- 02Reuses the LLM configured in the client
- 03Quick start with a uvx command
- 04Semantic versioning with tagged releases
Use cases
- 01Let an MCP client carry out web tasks in a browser
- 02Run browser automation without configuring a separate LLM API key
MCP support
This project is an MCP server that gives MCP clients browser control. It relies on the client's existing LLM instead of calling a model API itself.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-browser-use: MCP server for browser-use
mcp-browser-use is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.
Unlike other browser-use MCPs that make you pay for an LLM API key, this one just uses the LLM that's already set up in your MCP client.
Quickstart
You can start using mcp-browser-use with an MCP client by putting the following command in the relevant config:
uvx mcp-browser-use
Note: Provide the full path to uvx to prevent MCP client failing to start the server.
Contributing
Contributions are welcome! Please feel free to submit a pull request.
Versioning
mcp-browser-use uses Semantic Versioning. For the available versions, see the tags on the GitHub repository.
License
This project is licensed under the Apache 2.0 License, see the LICENSE file for details.
Comments
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.