Browser Use MCP Server

@Cam10001110101

Basic information

About Browser Use MCP Server

No overview available yet

Browser Use MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-browser-use-ollama": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-e",
        "."
      ]
    }
  }
}

Browser Use MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Browser Use MCP?

Browser Use MCP is a browser automation system that enables AI agents to control web browsers through the Model Context Protocol (MCP). It is designed to work with local AI models running via Ollama, allowing secure and efficient browser interactions using locally-hosted LLMs.

How to use Browser Use MCP?

Clone the repository, install dependencies with uv pip install -e . and run playwright install. Ensure Ollama is installed, running (ollama serve), and has a model pulled (e.g., ollama pull qwen3). Use the server via Claude Desktop by configuring the claude_desktop_config.json to point to src/server.py, or run the client directly with python src/client.py src/server.py [task].

Key features of Browser Use MCP

Full MCP integration for structured AI-browser communication
Optimized for local models via Ollama
Browser control with Playwright (Chrome, Firefox, Safari)
Screenshot capabilities for visual feedback and debugging
Session management with automatic cleanup
Interactive mode with continuous feedback loop between AI and browser state

Use cases of Browser Use MCP

Perform web searches and summarize results using natural language
Compare products on e‑commerce sites and generate structured tables
Conduct multi‑source research workflows, visiting several pages and compiling summaries
Execute complex, file‑based tasks loaded from a text file

Frequently asked questions

What is the default Ollama model used?

The default model is `qwen3`. You can change it by setting the `OLLAMA_MODEL` environment variable or passing the `--model` flag to the client.

What browsers does it support?

It supports Chrome, Firefox, and Safari through Playwright automation.

How does the system handle errors and cleanup?

Browser sessions are automatically cleaned up, and the system includes graceful recovery from parsing errors, with comprehensive logging for debugging.

What is the architecture of Browser Use MCP?

It uses a client‑server architecture with stdio‑based MCP transport: the user interacts with a client, which communicates via MCP with the server, which in turn controls the browser via Playwright.

Can I use a model other than the default?

Yes, any Ollama‑compatible model can be used. The system is optimized for coding models like `qwen3` and `qwen2.5-coder:7b`, and model selection is configurable via environment variables or command‑line arguments.