--- title: "Vibetest-Use (Automated QA)" description: "Run multi-agent Browser-Use tests to catch UI bugs, broken links, and accessibility issues before they ship." icon: "bug" mode: "wide" --- Requires **browser-use  < v0.5.0** and Playwright Chromium. Currently getting an update to v0.7.6+. ## Features 1. Launches multiple headless (or visible) Browser-Use agents in parallel 2. Crawls your site and records screenshots, broken links & a11y issues 3. Works on production URLs *and* `localhost` dev servers 4. Simple natural-language prompts via MCP in Cursor / Claude Code ## Quick Start ```bash # 1. Clone repo git clone https://github.com/browser-use/vibetest-use.git cd vibetest-use # 2. Create & activate env uv venv --python 3.11 source .venv/bin/activate # 3. Install project uv pip install -e . # 4. Install browser runtime once playwright install chromium --with-deps --no-shell ``` ### 1) Claude Code ```bash # Register the MCP server claude mcp add vibetest /full/path/to/vibetest-use/.venv/bin/vibetest-mcp \ -e GOOGLE_API_KEY="your_api_key" # Inside a Claude chat > /mcp # ⎿ MCP Server Status # • vibetest: connected ``` ### 2) Cursor (manual MCP entry) 1. Open **Settings → MCP** 2. Click **Add Server** and paste: ```json { "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:4242 with 10 agents ``` ### Parameters * **URL** – any `https` or `http` host or `localhost:port` * **Agents** – `3` by default; more agents = deeper coverage * **Headless** – say *headless* to hide the browser, omit to watch it live ## Requirements * Python 3.11+ * Google API key (Gemini flash used for analysis) * Cursor / Claude with MCP support ## Source Code Full implementation: [https://github.com/browser-use/vibetest-use](https://github.com/browser-use/vibetest-use)