MCP SERVER · OFFICIAL PROJECTRuns a browser agent in a cloud sandbox — start a task, follow up in the same session, and read every step it took.
LABSCO SUMMARY
Tools like Anchor give a model navigate and click; this one takes a sentence and decides the clicks itself. That is far less context per task and far less control, which is why get_session_messages matters: it is the only way to find out what it actually did. Two operational details worth planning for — browser profiles hold real logins, so a profile is a credential, and stop_session's task strategy lets you cancel a runaway step without losing the session's state.
Browser Use's v3 endpoint: seven tools around a session-based agent that runs in a cloud sandbox. The unit here is a session, not a click — you give it a task and it drives the browser itself.
An API key in the x-browser-use-api-key header. Sessions report their cost, so spend is visible per run.
Paste a URL with a key — add the endpoint to your client
USE CASES
Describe the goal and let the sandboxed agent work, polling for completion rather than scripting each step.
Send a follow-up into a keep-alive session so the browser state and login survive.
Read the agent's steps and reasoning, not just the final output.
Use a cloud browser profile that already holds the cookies rather than passing credentials in the task.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
run_sessionCreate 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_taskSend 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_sessionGet 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_messagesGet 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_sessionStop 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_sessionsList recent sessions for the authenticated project, with status and cost info.
list_browser_profilesList 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.
BEFORE YOU INSTALL
7 tools when we connected.
CONTEXT COST
Rated by the size of the 7 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Add the endpoint to your client.
https://api.browser-use.com/v3/mcpMCP servers
steel-dev
opentabs-dev
anthonybono21-cloud