Atlas / MCP servers / browser-use / Vibetest Use

Vibetest UseSAFE

mcp/browser-use/vibetest-use

Vibetest MCP - automated QA testing using Browser-Use agents

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 0r · 2w · 0d
Transport
—
License
—
Stars
831
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Automated QA testing using Browser-Use agents.

https://github.com/user-attachments/assets/9558d051-78bc-45fd-8694-9ac80eaf9494

An MCP server that launches multiple Browser-Use agents to test a vibe-coded website for UI bugs, broken links, accessibility issues, and other technical problems.

Perfect for testing both live websites and localhost development sites.

Vibecode and vibetest until your website works.

Quick Start

# Install dependencies
uv venv
source .venv/bin/activate
uv pip install -e .

# Install the browser
playwright install chromium --with-deps --no-shell

1) Claude Code

# Add MCP server via CLI
claude mcp add vibetest /full/path/to/vibetest-use/.venv/bin/vibetest-mcp -e GOOGLE_API_KEY="your_api_key"

# Test in Claude Code
> claude

> /mcp 
⎿  MCP Server Status

• vibetest: connected

2) Cursor (manually)

  1. Install via MCP Settings UI:
  2. Open Cursor Settings
  3. Click on "MCP" in the left sidebar
  4. Click "Add Server" or the "+" button
  5. Manually edit config:
{
"mcpServers": {
"vibetest": {
"command": "/full/path/to/vibetest-use/.venv/bin/vibetest-mcp",
"env": {
"GOOGLE_API_KEY": "your_api_key"
}
}
}
}

Basic Prompts

> Vibetest my website with 5 agents: browser-use.com
> Run vibetest on localhost:3000
> Run a headless vibetest on localhost:8080 with 10 agents

Parameters You Can Specify

  • URL: Any website (https://example.com, localhost:3000, http://dev.mysite.com)
  • Number of agents: 3 (default), 5 agents, 2 agents - more agents = more thorough testing
  • Headless mode: non-headless (default) or headless

Requirements

  • Python 3.11+
  • Google API key (get one) (we support gemini-2.0-flash)
  • Cursor/Claude with MCP support

Full Demo

https://github.com/user-attachments/assets/6450b5b7-10e5-4019-82a4-6d

Read from source at commit e013ffcc35c1OBSERVED · 2026-09-27
02

Connect

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-code
claude mcp add vibetest --env GOOGLE_API_KEY=${GOOGLE_API_KEY} -- uvx vibetest
claude-desktop
{
  "mcpServers": {
    "vibetest": {
      "command": "uvx",
      "args": [
        "vibetest"
      ],
      "env": {
        "GOOGLE_API_KEY": "${GOOGLE_API_KEY}"
      }
    }
  }
}
03

Exposed tools (2)

0 read · 2 write · 0 destructive.

ToolRiskDescription
resultswriteGet the consolidated bug report for a test run.
startwriteLaunch browser agents to test a website for UI bugs and issues.
04

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.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence

Gates applied: no_behavioural_pass, no_license.

Audited 2026-09-27 · audit v0.4.1 · source sha e013ffcc35c1full audit observations/trust-audit/mcp-server/browser-use__vibetest-use.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-09-27e013ffcc35c1SAFEB89first audit
06

Questions

What is the Vibetest Use MCP server?

Vibetest MCP - automated QA testing using Browser-Use agents

What tools does Vibetest Use expose?

2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Vibetest 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 Vibetest Use need?

It reads GOOGLE_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 (e013ffcc35c1), read on 2026-09-27. The repository is watched and re-audited when it changes.

Advertisement