Browser Use MCP by JovaniPink
JovaniPinkLABSCO SUMMARY
There is a second model inside, and it costs money.
The browsing is driven by the provider you configure, not by the assistant that called the tool — so one request can turn into a long chain of model calls on your key. That is also the appeal: a multi-step task completes without your assistant narrating every click. Pointing it at Ollama keeps the whole loop local if the cost matters more than the capability.
What it is
A FastMCP server that wraps browser-use, so an assistant can delegate a whole browsing task rather than issuing clicks. You give it an instruction — navigate here, search for this, summarize what you find — and it runs the steps itself in a real browser, driven by a model you choose at launch.
What you get
- Browser automation from natural language: navigating, filling forms, clicking buttons and other web tasks carried out as a sequence, not one call at a time
- A real Chromium via Playwright, so pages that need JavaScript behave as they would for a person
- Your choice of model behind it, set with
--modelat launch - A wide provider list — OpenAI, Anthropic, Google, Cohere, Mistral, Groq, Together, AWS Bedrock, Fireworks, Azure OpenAI, Vertex AI, NVIDIA, AI21, Databricks, IBM watsonx.ai, xAI, Upstage, Hugging Face, and local options through Ollama or Llama.cpp
--debugfor detailed logging when a run does something you did not expect
Requirements
An API key for whichever provider you pick — OPENAI_API_KEY, ANTHROPIC_API_KEY, GROQ_API_KEY and so on, or OLLAMA_BASE_URL to stay local. Install the package with the extra for your provider, or [all-providers] for everything, then playwright install chromium, which is the step most often skipped. The client config runs browser-use-mcp with --model in args and the key in env; set DISPLAY on a GUI environment. Package browser-use-mcp at 0.1.0, MIT.
Setup effort
One command plus a key — pip install -e "git+https://github.com/pietrozullo/browser-use-mcp.git#egg=browser-use-mcp[openai]", then supply credentials
USE CASES
01
Researching something that takes several pages
Give the whole task at once — navigate, search, read, summarize — instead of steering click by click.
02
Filling in a form on a site with no API
Describe what needs entering and let the agent work through the fields in a real browser.
03
Reaching a page that needs JavaScript
Chromium renders it properly, so the content is there to read rather than an empty shell.
04
Keeping the browsing model local
Point it at an Ollama base URL so no page content goes to a hosted provider.
BEFORE YOU INSTALL
What to know first
Requires
Python 3.11 or later; Playwright's Chromium (playwright install chromium); An API key for the provider behind --model: OPENAI_API_KEY for gpt-4o, ANTHROPIC_API_KEY for Claude models, or another provider's variable from the README (Ollama needs only OLLAMA_BASE_URL)
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install -e "git+https://github.com/pietrozullo/browser-use-mcp.git#egg=browser-use-mcp[openai]"Use the extra for your LLM provider in place of openai (the extras are named after the provider), or all-providers for every one. Then install Playwright's Chromium: playwright install chromium
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"browser-use": {
"command": "browser-use-mcp",
"args": [
"--model",
"claude-3-opus-20240229"
]
}
}
}This entry runs claude-3-opus-20240229, an Anthropic model, so the server needs ANTHROPIC_API_KEY: add "env": {"ANTHROPIC_API_KEY": "your-anthropic-api-key"} to it. The Anthropic library is part of the base install.
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"browser-use-mcp": {
"command": "browser-use-mcp",
"args": [
"--model",
"gpt-4o"
],
"env": {
"OPENAI_API_KEY": "your-openai-api-key",
"DISPLAY": ":0"
}
}
}
}Replace your-openai-api-key with your OpenAI key. For another provider, set its key variable instead (ANTHROPIC_API_KEY, GOOGLE_API_KEY and so on) and a --model that provider serves. DISPLAY is for GUI environments.
