Web UX Evaluator MCP server for AI agents

The operative.sh web-eval-agent MCP Server is a powerful tool that allows coding agents to autonomously execute and debug web applications directly in your code editor. It uses browser automation to test functionality, capture network traffic, and collect console errors, enabling efficient end-to-end testing and debugging.

Installation

Quick Installation (macOS/Linux)

Ensure you have the prerequisites (usually not needed):

Install Homebrew (if not already installed):

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Install npm:
```
brew install npm
```
Install jq:
```
brew install jq
```

Run the installer after getting an API key (free):

curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh

Restart your code editor (Cursor/Cline/Windsurf) to apply the changes

Use the web-eval-agent by sending a prompt in chat mode:

Test my app on http://localhost:3000. Use web-eval-agent.

Manual Installation

Get your API key at operative.sh

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 the following JSON to your code editor configuration with your API key:

"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>"
  }
}

Restart your code editor

Manual Installation (Windows)

Open your code editor terminal and run:

curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh

Get your API key at operative.sh

Install uv:

curl -LsSf https://astral.sh/uv/install.sh | sh

Install playwright components:

uvx --from git+https://github.com/Operative-Sh/web-eval-agent.git playwright install

Restart your code editor

Updating

To update the MCP server:

uv cache clean

Then restart your code editor.

Usage

MCP Tool Reference

web_eval_agent

This tool automatically evaluates your web application by driving the browser, capturing screenshots, console logs, and network activity.

Required arguments:

url - Address of the running app (e.g., http://localhost:3000)
task - Natural language description of what to test (e.g., "run through the signup flow and note any UX issues")

Optional arguments:

headless_browser - Set to true to hide the browser window (default: false)

setup_browser_state

Opens an interactive (non-headless) browser so you can sign in once. The saved cookies and local storage are reused by subsequent web_eval_agent runs.

Optional arguments:

url - Page to open first (useful for landing directly on a login screen)

Example Usage

In your IDE chat, you can trigger these tools with natural language:

Evaluate my app at http://localhost:3000 – run web_eval_agent with the task "Try the full signup flow and report UX issues".

Example Output

The web-eval-agent provides detailed reports including:

Agent steps taken during testing
Console logs
Network requests
Chronological timeline of events

For example:

📊 Web Evaluation Report for http://localhost:5173 complete!
📝 Task: Test the API-key deletion flow

🔍 Agent Steps
  📍 1. Navigate → http://localhost:5173
  📍 2. Click     "Login"        (button index 2)
  📍 3. Click     "API Keys"     (button index 4)
  ...

🖥️ Console Logs (10)
  1. [debug] [vite] connecting…
  ...

🌐 Network Requests (10)
  1. GET /src/pages/SleepingMasks.tsx                   304
  ...

⏱️ Chronological Timeline
  01:16:23.293 🖥️ Console [debug] [vite] connecting…
  ...

Troubleshooting

If updates aren't being received in code editors, run uv cache clean and restart
For issues with static apps not screencasting, run uv clean and restart

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.