---
title: "Browser Use MCP server: an autonomous browser agent for AI tools"
canonical_url: https://cookiesforai.app/mcp/browser-use
last_updated: 2026-10-03T10:04:47+02:00
type: mcp
summary: "The Browser Use MCP server gives AI agents the Browser Use browsing agent, either as a local open-source server with direct browser tools or as a cloud server that runs whole web tasks."
install: "claude mcp add -t http -H \"x-browser-use-api-key: YOUR_API_KEY\" browser-use https://api.browser-use.com/v3/mcp"
related:
  - "https://cookiesforai.app/mcp/browserbase"
  - "https://cookiesforai.app/mcp/chrome-devtools"
  - "https://cookiesforai.app/mcp/playwright"
---

# Browser Use MCP server

The Browser Use MCP server gives AI agents the Browser Use browsing agent, either as a local open-source server with direct browser tools or as a cloud server that runs whole web tasks.

| Fact | Value |
|---|---|
| Publisher | Browser Use (official) |
| Source | https://github.com/browser-use/browser-use |
| License | MIT |
| GitHub stars | 116,955 on 2026-10-02 |
| Last code push | 2026-10-01 |
| Page updated | 2026-10-03 |
| Hosted endpoint | https://api.browser-use.com/v3/mcp |
| Official MCP Registry | com.browser-use/browser-use |
| Documented clients | Claude Code, Claude Desktop, Cursor, Windsurf |
| Category | Browser automation and testing |
| Free tier | Free plan |
| Cost | The local server is free and open source under MIT and uses your own LLM API key; the cloud server is pay as you go, with free signup credit for eligible accounts. |
| Current prices | https://browser-use.com/pricing |
| Facts checked | 2026-10-02 |

## Connect

Claude Code, cloud server:

```
claude mcp add -t http -H "x-browser-use-api-key: YOUR_API_KEY" browser-use https://api.browser-use.com/v3/mcp
```

Cursor or Claude Desktop, cloud server:

```
{"mcpServers": {"browser-use": {"url": "https://api.browser-use.com/v3/mcp", "headers": {"x-browser-use-api-key": "YOUR_API_KEY"}}}}
```

Claude Code, local open-source server:

```
claude mcp add browser-use -- uvx --from 'browser-use[cli]' browser-use --mcp
```

Get a cloud API key at cloud.browser-use.com. For the local server, set OPENAI_API_KEY or ANTHROPIC_API_KEY in its environment, and in Claude Desktop use the full path to uvx if the app cannot find it.

## Ask your coding agent

```text
Connect the Browser Use MCP server to my coding agent using its documented setup: https://github.com/browser-use/browser-use.
```

## What it does

The Browser Use MCP server connects an AI agent to Browser Use, an open-source library in which a language model operates a real Chrome browser to finish a task. It comes in two forms. The cloud server takes a whole task in plain words, such as finding a flight or filling in an application, runs it in Browser Use's cloud browsers, and reports status, cost, a live view URL and the result, optionally shaped by a JSON schema.

The local server runs on your machine through uvx and gives the agent lower-level tools: navigate, click and type by element index, read the page state, scroll, manage tabs, extract content, get HTML and take screenshots. When direct control fails, a fallback tool hands the whole task to the Browser Use agent. Cloud sessions can keep the browser alive for follow-up tasks and use saved browser profiles for sites that need a login.

The browser-use repo on GitHub, which holds the local MCP server, had 116,895 stars on 2026-10-01. Those stars are for the whole library, not for the MCP server alone.

Tools it gives your agent: `run_session`, `get_session`, `send_task`, `stop_session`, `list_sessions`, `list_browser_profiles`, `browser_navigate`, `browser_click`, `browser_type`, `browser_get_state`, `browser_extract_content`, `retry_with_browser_use_agent`

## When to use it

- You want to hand off a whole web chore, like comparing prices on several shops, and get back the result.
- You need a browser task to run in the cloud while your own machine stays free.
- You already use the Browser Use library and want the same agent inside your editor.
- A task needs a logged-in session that you saved as a browser profile.

## When to pick something else

- Cost control without watching: each run spends model tokens plus browser time, and the local server needs your own LLM API key.
- Step-by-step deterministic testing; Playwright MCP gives exact, repeatable actions.

## What it needs

- Cloud: a Browser Use Cloud API key
- Local: Python with uv, Chrome, and an OpenAI or Anthropic API key

## Related

### Other MCP servers for browser automation and testing

- [Browserbase](https://cookiesforai.app/mcp/browserbase): The Browserbase MCP server gives AI agents a browser that runs in Browserbase's cloud, controlled with plain-language commands through Stagehand: navigate, act on the page, observe elements and extract data.
- [Chrome DevTools](https://cookiesforai.app/mcp/chrome-devtools): The Chrome DevTools MCP server gives AI agents control of a live Chrome browser with DevTools access: performance traces, network requests, console errors, Lighthouse audits, memory snapshots and page automation.
- [Playwright](https://cookiesforai.app/mcp/playwright): The Playwright MCP server gives AI agents a real browser driven by Microsoft's Playwright: navigate, click, type and fill forms using the page's accessibility tree instead of screenshots.