
Browser Use
Browser agents and cloud browsers for AI, with an MCP server for web tasks
Answered our latest tool-list check 9 hours ago with 7 tools. It will be marked verified after 3 successful checks in 7 days.
- Pricing
- Freemium
- Platforms
- API, CLI, Web
- Runs
- Locally or Remotely
- GitHub stars
- 121K
- Last commit
- today
- Language
- Python
About Browser Use
Browser Use is a freemium MCP server for browser automation. It can run locally on your machine or as a hosted remote server.
Browser Use provides browser agents and hosted cloud browsers that AI systems can drive to complete web tasks such as filling forms and extracting data. It offers an open-source Python package and a remote MCP endpoint.
The hosted side is billed pay as you go with no subscription, with cloud browsers priced per hour and proxy traffic per gigabyte. The site also mentions a Browser Harness for coding agents, US and EU regions, on-prem options and SOC 2 Type II.
It is aimed at developers and teams who want agents to operate real websites, including ones with bot checks.
Install
Run in a terminal
claude mcp add --transport http browser-use https://api.browser-use.com/v3/mcpAdd to Settings → Connectors → Add custom connector
https://api.browser-use.com/v3/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"browser-use": {
"url": "https://api.browser-use.com/v3/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"browser-use": {
"type": "http",
"url": "https://api.browser-use.com/v3/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"browser-use": {
"serverUrl": "https://api.browser-use.com/v3/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"browser-use": {
"type": "http",
"url": "https://api.browser-use.com/v3/mcp"
}
}
}Tools this server provides (7)
Read directly from the server.
- run_session
- Create a new browser agent session and run a task. This uses the v3 sandbox-based agent that supports long-running sessions, workspaces, and keep-alive. After creating a session, call get_session to poll for status and output. For tasks requiring authentication, use list_browser_profiles first to get a profile_id.
- send_task
- Send a follow-up task to an existing keep-alive session. The session must be in idle status. Use this for multi-turn interactions where you want to reuse the same browser context.
- get_session
- Get current status and output of a session. Call this repeatedly to poll for task completion. Returns status (created, idle, running, stopped, timed_out, error), step count, output, cost breakdown, and live URL.
- get_session_messages
- Get the agent messages/steps for a session. Shows what the agent is doing including browser actions, reasoning, and results. Use after= parameter for pagination to get new messages since your last check.
- stop_session
- Stop a running session. Use strategy "task" to stop only the current task (session stays idle for follow-ups), or "session" (default) to destroy the sandbox entirely.
- list_sessions
- List recent sessions for the authenticated project, with status and cost info.
- list_browser_profiles
- List all available cloud browser profiles for the authenticated project. Profiles store persistent authentication (cookies, sessions) for websites requiring login. Use this BEFORE attempting any authenticated tasks. Show profiles to the user and let them choose, then pass the selected profile_id to run_session.
What it does
- Web agents
- Send a task and receive structured JSON results.
- Stealth cloud browsers
- Hosted browsers meant to get past bot checks, billed per hour.
- Browser Harness
- A tool aimed at coding agents such as Claude Code and Codex.
- Open-source package
- MIT-licensed Python package installable from PyPI.
- Remote MCP endpoint
- A streamable-http MCP server is available alongside the stdio package.
- Enterprise options
- On-prem, US or EU cloud, SOC 2 Type II and HIPAA on enterprise plans.
Good for
- Fill in web forms automatically
- Extract data from websites
- Run shopping or checkout tasks with an agent
- Give a coding agent a browser
- Test agents against sites with bot protection
Pricing
Freemium
Open-source package; cloud pay as you go, $0.06/browser-hour, $1 free credit
Prices change. Check browser-use.com before you buy.
Browser Use FAQ
How is the cloud priced?
Pay as you go with no subscription; cloud browsers are listed at $0.06 per hour and credits do not expire.
Is there a free start?
The site offers $1 of free credit, one per person.
Is the code open source?
The repository is MIT licensed.
Does it support EU data residency?
The site says EU runs stay in Frankfurt.
Is Browser Use free?
Browser Use has a free plan, with paid plans for more usage or features.
How do I add Browser Use to Claude Code?
Run this command in your terminal: claude mcp add --transport http browser-use https://api.browser-use.com/v3/mcp
What are the best alternatives to Browser Use?
The closest alternatives to Browser Use are Scrapling MCP Server, Oya Browser, Mantis, Auto-building agents and pour.
Alternatives to Browser Use

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Oya Browser
MCP serverHIPAA-oriented agentic browser with replayable playbooks, reachable over MCP
- 32 tools
- Remote
- Freemium
- 349 GitHub stars
- Browser automation
Mantis
MCP serverBrowser MCP server that gives agents numbered text pages instead of screenshots
Runs locally- 1 tool
- Open source
- 5 Hacker News points
- Browser automation

Auto-building agents
MCP serverBuild and continue browser and Mac automation scripts for Super through Claude
- Remote
- Paid
- Browser automation

pour
MCP serverRun WCAG 2.2 accessibility audits and vision simulations on any URL from an agent
Runs locally- Open source
- Developer tools

AgentFarm
MCP serverLets your AI agent browse as you, in a real browser on your Mac
Not checked yet- Remote
- Freemium
- Browser automation