# com.browser-use/browser-use (remote · api.browser-use.com)

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

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `api.browser-use.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/com-browser-use-browser-use/v3-mcp.md), [page](https://verifymcp.io/servers/com-browser-use-browser-use/v3-mcp)
- pypi · `browser-use`: 0/100, [markdown](https://verifymcp.io/servers/com-browser-use-browser-use/browser-use.md), [page](https://verifymcp.io/servers/com-browser-use-browser-use/browser-use)

## Channel facts

- Endpoint: `https://api.browser-use.com/v3/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `0.13.11`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 826 tokens (~118/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_task" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the com.browser-use/browser-use MCP server?

com.browser-use/browser-use is a hosted endpoint at https://api.browser-use.com/v3/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-browser-use-browser-use 'https://api.browser-use.com/v3/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-browser-use-browser-use": {
      "url": "https://api.browser-use.com/v3/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-browser-use-browser-use": {
      "type": "http",
      "url": "https://api.browser-use.com/v3/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-browser-use-browser-use]
url = "https://api.browser-use.com/v3/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-browser-use-browser-use": {
      "type": "remote",
      "url": "https://api.browser-use.com/v3/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-browser-use-browser-use --url 'https://api.browser-use.com/v3/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-browser-use-browser-use:
    url: "https://api.browser-use.com/v3/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-browser-use-browser-use": {
      "Transport": "http",
      "Url": "https://api.browser-use.com/v3/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-browser-use-browser-use -t streamable-http -u 'https://api.browser-use.com/v3/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-browser-use-browser-use": {
      "type": "http",
      "url": "https://api.browser-use.com/v3/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 71, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-21 (score 71)

First indexed and scored.

## MCP tools (7)

### `run_session` (~355 tokens)

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.

Input parameters:

- `keep_alive` (boolean): If true, the session stays idle after the task finishes, ready for follow-up tasks via send_task. Default is false (session auto-stops).
- `model` (string): Agent model to use. When omitted, an account-appropriate default is selected. Available: gemini-3-flash, claude-sonnet-5, claude-opus-4.6, claude-opus-4.7, claude-opus-4.8, gpt-5.4-mini, glm-5.2, min…
- `output_schema` (object): JSON schema for structured output. The agent will return data matching this schema.
- `profile_id` (string): UUID of the cloud profile to use for authenticated tasks. Get this from list_browser_profiles.
- `proxy_country`: ISO 3166-1 alpha-2 country code for the proxy location (e.g. "us", "gb", "de", "jp", "br"). Defaults to "us" if not specified. Set to null to disable the proxy.
- `task` (string, required): Detailed instructions for what you want the browser agent to do.
- `workspace_id` (string): UUID of the workspace for file persistence across sessions.

### `send_task` (~114 tokens)

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.

Input parameters:

- `keep_alive` (boolean): If true, session stays idle after this task too. Default is false.
- `output_schema` (object): JSON schema for structured output.
- `session_id` (string, required): UUID of an existing idle session (from run_session with keep_alive=true).
- `task` (string, required): The follow-up task instructions.

### `get_session` (~68 tokens)

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.

Input parameters:

- `session_id` (string, required): UUID of the session to check.

### `get_session_messages` (~97 tokens)

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.

Input parameters:

- `after` (string): Return messages after this message ID (cursor-based pagination). Omit for initial fetch.
- `limit` (integer): Max number of messages to return.
- `session_id` (string, required): UUID of the session.

### `stop_session` (~84 tokens)

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.

Input parameters:

- `session_id` (string, required): UUID of the session to stop.
- `strategy` (string): Stop strategy: "task" stops the current task only, "session" destroys the sandbox.

### `list_sessions` (~46 tokens)

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

Input parameters:

- `page` (integer): Page number (1-indexed).
- `page_size` (integer): Results per page.

### `list_browser_profiles` (~62 tokens)

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.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-browser-use-browser-use/v3-mcp#diagnostics

## Score history

- 2026-10-23: 72
- 2026-10-22: 71
- 2026-10-21: 71

## Common questions

### What is the com.browser-use/browser-use MCP server?

com.browser-use/browser-use is an MCP server listed in the public MCP registry as com.browser-use/browser-use. Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data. This page covers its hosted endpoint (https://api.browser-use.com/v3/mcp).

### Is the com.browser-use/browser-use MCP server safe to use?

com.browser-use/browser-use scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the com.browser-use/browser-use MCP server expose?

com.browser-use/browser-use exposes 7 tools: run_session, send_task, get_session, get_session_messages, stop_session, and 2 more. Their descriptions and schemas cost roughly 826 tokens of context every time the server is loaded.

### Does the com.browser-use/browser-use MCP server require authentication?

Yes. com.browser-use/browser-use asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the com.browser-use/browser-use MCP server still maintained?

com.browser-use/browser-use is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.browser-use.com/v3/mcp
- Authorisation metadata: https://api.browser-use.com/.well-known/oauth-protected-resource/v3/mcp
- Repository: https://github.com/browser-use/browser-use
- Website: https://browser-use.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-browser-use-browser-use/v3-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-browser-use-browser-use/v3-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-browser-use-browser-use/v3-mcp