Browser UseSAFE
FastAPI MCP server that exposes browser-use automation through a testable Model Context Protocol boundary.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@JovaniPink/mcp-browser-use)
Model Context Protocol (MCP) server that wires browser-use into Claude Desktop and other MCP compatible clients.
Overview
This repository provides a beta MCP wrapper around the browser-use automation engine. It exposes a single MCP tool (run_browser_agent) that orchestrates a browser session, executes the browser-use agent, and returns the final result to the client. The layout keeps configuration in one place, makes security boundaries testable, and isolates upstream browser-use migrations from the MCP interface.
Key Capabilities
- Automated browsing – Navigate, interact with forms, control tabs, capture screenshots, and read page content through natural-language instructions executed by
browser-use. - Agent lifecycle management –
CustomAgentwrapsbrowser-use's base agent to add history export, richer prompts, and consistent error handling across runs. - Centralised browser configuration –
create_browser_sessiontranslates environment variables into a ready-to-useBrowserSession, enabling persistent profiles, proxies, and custom Chromium flags without touching the agent logic. - FastMCP integration –
server.pyregisters the MCP tool, normalises configuration, and ensures the browser session is always cleaned up. - Client helpers –
client.pyincludes async helpers for tests or other Python processes that wish to exercise the MCP server in-process.
Project Structure
. ├── documentation/ │ ├── CONFIGURATION.md # Detailed configuration reference │ └── SECURITY.md # Security considerations for running the server ├
cb6045028793OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp_browser_use --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env AZURE_OPENAI_API_KEY=${AZURE_OPENAI_API_KEY} --env BROWSER_USE_PROXY_PASSWORD=${BROWSER_USE_PROXY_PASSWORD} --env DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY} -- uvx mcp_browser_use{
"mcpServers": {
"mcp_browser_use": {
"command": "uvx",
"args": [
"mcp_browser_use"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"AZURE_OPENAI_API_KEY": "${AZURE_OPENAI_API_KEY}",
"BROWSER_USE_PROXY_PASSWORD": "${BROWSER_USE_PROXY_PASSWORD}",
"DEEPSEEK_API_KEY": "${DEEPSEEK_API_KEY}"
}
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
run_browser_agent | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (6)
importlib.import_module(legacy_module)
importlib.import_module(module_name)
importlib.import_module(module_name)
img_data = base64.b64decode(item.state.screenshot)
img = Image.open(io.BytesIO(base64.b64decode(screenshot_b64))).convert("RGBA")Gates applied: no_behavioural_pass, no_license.
cb6045028793full audit observations/trust-audit/mcp-server/jovanipink__browser-use-6.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | cb6045028793 | SAFE | B | 89 | first audit |
Questions
What is the Browser Use MCP server?
FastAPI MCP server that exposes browser-use automation through a testable Model Context Protocol boundary.
What tools does Browser Use expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Browser Use safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Browser Use need?
It reads ANTHROPIC_API_KEY, AZURE_OPENAI_API_KEY, BROWSER_USE_PROXY_PASSWORD, DEEPSEEK_API_KEY, GOOGLE_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (cb6045028793), read on 2026-10-07. The repository is watched and re-audited when it changes.