web-eval-agent
3.8
If you are the rightful owner of web-eval-agent and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
operative.sh's MCP Server is a tool for autonomous debugging of web applications directly from your code editor.
๐ operative.sh web-eval-agent MCP Server
Let the coding agent debug itself, you've got better things to do.
๐ฅ Supercharge Your Debugging
operative.sh's MCP Server launches a browser-use powered agent to autonomously execute and debug web apps directly in your code editor.
โก Features
- ๐ Navigate your webapp using BrowserUse (2x faster with operative backend)
- ๐ Capture network traffic - requests are intelligently filtered and returned into the context window
- ๐จ Collect console errors - captures logs & errors
- ๐ค Autonomous debugging - the Cursor agent calls the web QA agent mcp server to test if the code it wrote works as epected end-to-end.
๐งฐ MCP Tool Reference
| Tool | Purpose |
|---|---|
web_eval_agent | ๐ค Automated UX evaluator that drives the browser, captures screenshots, console & network logs, and returns a rich UX report. |
setup_browser_state | ๐ 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_agenturl(required) โ address of the running app (e.g.http://localhost:3000)task(required) โ natural-language description of what to test ("run through the signup flow and note any UX issues")headless_browser(optional, defaultfalse) โ set totrueto hide the browser window
-
setup_browser_stateurl(optional) โ 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 โ run web_eval_agent with the task "Try the full signup flow and report UX issues".
๐ Quick Start (macOS/Linux)
- Pre-requisites (typically not needed):
- brew:
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" - npm: (
brew install npm) - jq:
brew install jq
- Run the installer after getting an api key (free)
- Installs playwright
- Installs uv
- Inserts JSON into your code editor (Cursor/Cline/Windsurf) for you!
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh
- Visit your favorite IDE and restart to apply the changes
- Send a prompt in chat mode to call the web eval agent tool! e.g.
Test my app on http://localhost:3000. Use web-eval-agent.
๐ ๏ธ Manual Installation
- Get your API key at operative.sh/mcp
- Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
- Source environment variables after installing UV
Mac
source ~/.zshrc
Linux
source ~/.bashrc
- Install playwright:
npm install -g chromium playwright && uvx --with playwright playwright install --with-deps
- Add below JSON to your relevant code editor with api key
- Restart your code editor
๐ Updating
uv cache clean- refresh MCP server
"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>"
}
}
Operative Discord Server
๐ ๏ธ Manual Installation (Mac + Cursor/Cline/Windsurf)
- Get your API key at operative.sh/mcp
- Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh)
- Install playwright:
npm install -g chromium playwright && uvx --with playwright playwright install --with-deps
- Add below JSON to your relevant code editor with api key
- Restart your code editor
Manual Installation (Windows + Cursor/Cline/Windsurf)
We're refining this, please open an issue if you have any issues!
- Do all this in your code editor terminal
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh- Get your API key at operative.sh/mcp
- Install uv
(curl -LsSf https://astral.sh/uv/install.sh | sh) uvx --from git+https://github.com/Operative-Sh/web-eval-agent.git playwright install- Restart code editor
๐จ Issues
- Updates aren't being received in code editors, update or reinstall for latest version: Run
uv cache cleanfor latest - Any issues feel free to open an Issue on this repo or in the discord!
- 5/5 - static apps without changes weren't screencasting, fixed!
uv clean+ restart to get fix
Changelog
- 4/29 - Agent overlay update - pause/play/stop agent run in the browser
๐ Example MCP Server Output Report
๐ Web Evaluation Report for http://localhost:5173 complete!
๐ Task: Test the API-key deletion flow by navigating to the API Keys section, deleting a key, and judging the UX.
๐ Agent Steps
๐ 1. Navigate โ http://localhost:5173
๐ 2. Click "Login" (button index 2)
๐ 3. Click "API Keys" (button index 4)
๐ 4. Click "Create Key" (button index 9)
๐ 5. Type "Test API Key" (input index 2)
๐ 6. Click "Done" (button index 3)
๐ 7. Click "Delete" (button index 10)
๐ 8. Click "Delete" (confirm index 3)
๐ Flow tested successfully โ UX felt smooth and intuitive.
๐ฅ๏ธ Console Logs (10)
1. [debug] [vite] connectingโฆ
2. [debug] [vite] connected.
3. [info] Download the React DevTools โฆ
โฆ
๐ Network Requests (10)
1. GET /src/pages/SleepingMasks.tsx 304
2. GET /src/pages/MCPRegistryRegistry.tsx 304
โฆ
โฑ๏ธ Chronological Timeline
01:16:23.293 ๐ฅ๏ธ Console [debug] [vite] connectingโฆ
01:16:23.303 ๐ฅ๏ธ Console [debug] [vite] connected.
01:16:23.312 โก๏ธ GET /src/pages/SleepingMasks.tsx
01:16:23.318 โฌ
๏ธ 304 /src/pages/SleepingMasks.tsx
โฆ
01:17:45.038 ๐ค ๐ Flow finished โ deletion verified
01:17:47.038 ๐ค ๐ Conclusion repeated above
๐๏ธ See the "Operative Control Center" dashboard for live logs.
Star History
Built with <3 @ operative.sh
