Skip to main content
Glama
Sign In

browser-use

by com.browser-use
OverviewDiscussionsAdmin

Server Details

Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2024-11-05
URL
Repository
browser-use/browser-use
GitHub Stars
70,259
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 7 tools

Disambiguation4/5

Each tool has a distinct purpose: session lifecycle (run/stop/send), status retrieval (get_session), step inspection (get_session_messages), and listing (list_sessions/list_browser_profiles). The trio of get_session, get_session_messages, and list_sessions share the 'session' subject and could momentarily overlap, but descriptions clearly differentiate polling status from reading step details from enumerating sessions.

Naming Consistency5/5

All seven tools use consistent snake_case with a clear verb_noun pattern (get_session, list_sessions, run_session, send_task, stop_session). The convention is predictable throughout with no camelCase or stylistic mixing.

Tool Count5/5

Seven tools is well-scoped for managing browser agent sessions, covering creation, monitoring, follow-up, listing, and teardown without redundancy. Each tool earns its place in the workflow.

Completeness4/5

The session lifecycle is well covered: create/run, poll status, inspect messages, list, send follow-ups, and stop. A minor gap exists around profile management (only list, no create/delete) and no explicit session cleanup beyond stop, but core workflows are fully supported.

Available Tools

7 tools
get_sessionAInspect

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.

Inputs: session_id (required).

get_session_messagesAInspect

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.

Inputs: session_id (required), after, limit.

list_browser_profilesAInspect

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.

Inputs: no named parameters.

list_sessionsBInspect

List recent sessions for the authenticated project, with status and cost info.

Inputs: page, page_size.

run_sessionAInspect

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.

Inputs: task (required), model, keep_alive, profile_id, +3 more.

send_taskAInspect

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.

Inputs: task (required), session_id (required), keep_alive, output_schema.

stop_sessionAInspect

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.

Inputs: session_id (required), strategy.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources