web-eval-agent
OfficialAutonomous browser agent that evaluates and debugs your web app end-to-end from your IDE.
Add to your client
Copy the config for your MCP client and paste it into its config file.
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.shPaste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"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>"
}
}
}
}Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.
Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf
Before you start
- A free OPERATIVE_API_KEY from operative.sh/mcp
- uv (installed via curl -LsSf https://astral.sh/uv/install.sh | sh)
- Playwright with Chromium (npm install -g chromium playwright && uvx --with playwright playwright install --with-deps)
- A running web app to evaluate (e.g. http://localhost:3000)
About web-eval-agent
An MCP server from operative.sh that autonomously evaluates web applications. It launches a BrowserUse/Playwright-powered agent that navigates your running webapp, captures network traffic and console errors, and returns a UX report so a coding agent can debug itself. Installs via a one-click integration or a manual uvx setup, and is intended to be called from IDE chat in Cursor, Cline, or Windsurf.
Tools & capabilities (2)
web_eval_agentAutomated UX evaluator that drives the browser to perform a natural-language task, captures screenshots, console & network logs, and returns a rich UX report. Required args: url (address of the running app, e.g. http://localhost:3000) and task (what to test). Optional: headless_browser (default false; set true to hide the browser window).
setup_browser_stateOpens an interactive (non-headless) browser so you can sign in once; the saved cookies/local-storage are reused by subsequent web_eval_agent runs. Optional arg: url (page to open first, handy to land directly on a login screen).
What this server can do
web-eval-agent provides tools for these capabilities — tap one to see every MCP server that does the same:
When to use it
- Have a coding agent automatically test that a feature it just wrote works end-to-end
- Run through flows like signup or login and get a report of UX issues
- Capture console errors and filtered network requests during an automated browser run
- Sign in once and reuse the authenticated session across multiple evaluation runs
Security notes
Requires a free OPERATIVE_API_KEY from operative.sh/mcp, passed via the env block. The agent drives a real browser against your running app and can sign in via setup_browser_state, which persists cookies and local-storage locally for reuse. Note: this project has been discontinued by its maintainers.
web-eval-agent FAQ
Is this project still maintained?
No. The README states the project has been sunset/discontinued; the maintainers are building something new at withrefresh.com.
How do I get an API key?
Get a free API key at operative.sh/mcp. When you create it you also get an 'Add to Cursor' deeplink and a prefilled Claude Code command with the key included.
Updates aren't showing up in my editor. What do I do?
Run `uv cache clean` and refresh/restart the MCP server in your code editor to pull the latest version.
Does it run on Windows?
Yes, via the install.sh script and uvx, though the README notes Windows support is still being refined.
Alternatives to web-eval-agent
Compare all alternatives →
All-in-one web access MCP — Web Unlocker, SERP, Scraper API, and a cloud Scraping Browser.
Popular community Playwright + API testing MCP server with codegen, screenshots, and device emulation.
Official Browserbase cloud-browser MCP built on Stagehand — natural-language act/extract/observe.