An MCP Server that autonomously debugs web applications with browser-use browser agents
Add to Claude Desktop config.json
{
"mcpServers": {
"refreshdotdev-web-eval-agent": {
"command": "python",
"args": [
"-m",
"web_eval_agent"
]
}
}
} Get the source and run locally
git clone https://github.com/refreshdotdev/web-eval-agent.git ~/.mcp/web-eval-agent
cd ~/.mcp/web-eval-agent Let the coding agent debug itself, you’ve got better things to do.

operative.sh’s MCP Server launches a browser-use powered agent to autonomously execute and debug web apps directly in your code editor.
| Tool | Purpose |
|---|---|
web_eval_agent | 🤖 Automated UX evaluator that drives the browser, captures screenshots, console & network logs, and returns a rich UX report. |
setup_browser_state | 🔒 Opens an interactive (non-headless) browser so you can sign in once; the saved cookies/local-storage are reused by subsequent web_eval_agent runs. |
Key arguments
web_eval_agent
url (required) – address of the running app (e.g. http://localhost:3000)task (required) – natural-language description of what to test (“run through the signup flow and note any UX issues”)headless_browser (optional, default false) – set to true to hide the browser windowsetup_browser_state
url (optional) – page to open first (handy to land directly on a login screen)You can trigger these tools straight from your IDE chat, for example:
Evaluate my app at http://localhost:3000 – run web_eval_agent with the task "Try the full signup flow and report UX issues".
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"brew install npm)brew install jqcurl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh
Test my app on http://localhost:3000. Use web-eval-agent.
curl -LsSf https://astral.sh/uv/install.sh | sh
Mac
source ~/.zshrc
Linux
source ~/.bashrc
npm install -g chromium playwright && uvx --with playwright playwright install --with-deps
uv cache clean "web-eval-agent": {
"command": "uvx",
"args": [
"--refresh-package",
"webEvalAgent",
"--from",
"git+https://github.com/Operative-Sh/web-eval-agent.git",
"webEvalAgent"
],
"env": {
"OPERATIVE_API_KEY": "<YOUR_KEY>"
}
}
curl -LsSf https://astral.sh/uv/install.sh | sh)
npm install -g chromium playwright && uvx --with playwright playwright install --with-deps
We’re refining this, please open an issue if you have any issues!
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh(curl -LsSf https://astral.sh/uv/install.sh | sh)uvx --from git+https://github.com/Operative-Sh/web-eval-agent.git playwright installuv cache clean for latestuv clean + restart to get fix📊 Web Evaluation Report for http://localhost:5173 complete!
📝 Task: Test the API-key deletion flow by navigating to the API Keys section, deleting a key, and judging the UX.
🔍 Agent Steps
📍 1. Navigate → http://localhost:5173
📍 2. Click "Login" (button index 2)
📍 3. Click "API Keys" (button index 4)
📍 4. Click "Create Key" (button index 9)
📍 5. Type "Test API Key" (input index 2)
📍 6. Click "Done" (button index 3)
📍 7. Click "Delete" (button index 10)
📍 8. Click "Delete" (confirm index 3)
🏁 Flow tested successfully – UX felt smooth and intuitive.
🖥️ Console Logs (10)
1. [debug] [vite] connecting…
2. [debug] [vite] connected.
3. [info] Download the React DevTools …
…
🌐 Network Requests (10)
1. GET /src/pages/SleepingMasks.tsx 304
2. GET /src/pages/MCPRegistryRegistry.tsx 304
…
⏱️ Chronological Timeline
01:16:23.293 🖥️ Console [debug] [vite] connecting…
01:16:23.303 🖥️ Console [debug] [vite] connected.
01:16:23.312 ➡️ GET /src/pages/SleepingMasks.tsx
01:16:23.318 ⬅️ 304 /src/pages/SleepingMasks.tsx
…
01:17:45.038 🤖 🏁 Flow finished – deletion verified
01:17:47.038 🤖 📋 Conclusion repeated above
👁️ See the "Operative Control Center" dashboard for live logs.
Built with <3 @ operative.sh
Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
Automates browser-based workflows using LLMs and computer vision — navigate pages, fill forms, extract data, handle authentication, and automate any website via natural language
Automate your local Chrome browser
An MCP server using Playwright for browser automation and webscrapping
Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)