# WebOperator MCP server

> Exposes your live Chrome or Brave browser tabs to MCP clients to automate navigation, clicking, typing, and data extraction.

- Repository: https://github.com/KazKozDev/WebOperator
- Page: https://hostedmcp.org/servers/kazkozdev/weboperator
- Transport: stdio
- Stars: 4
- License: MIT
- Latest version: 1.5.1

## Install

### Claude Code

```sh
claude mcp add --env 'WEBOPERATOR_API_TOKEN=<YOUR_WEBOPERATOR_API_TOKEN>' weboperator -- npx -y weboperator-mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "weboperator": {
      "command": "npx",
      "args": [
        "-y",
        "weboperator-mcp"
      ],
      "env": {
        "WEBOPERATOR_API_TOKEN": "<YOUR_WEBOPERATOR_API_TOKEN>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "weboperator": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "weboperator-mcp"
      ],
      "env": {
        "WEBOPERATOR_API_TOKEN": "<YOUR_WEBOPERATOR_API_TOKEN>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"weboperator","type":"stdio","command":"npx","args":["-y","weboperator-mcp"],"env":{"WEBOPERATOR_API_TOKEN":"<YOUR_WEBOPERATOR_API_TOKEN>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "weboperator": {
      "command": "npx",
      "args": [
        "-y",
        "weboperator-mcp"
      ],
      "env": {
        "WEBOPERATOR_API_TOKEN": "<YOUR_WEBOPERATOR_API_TOKEN>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add weboperator --env 'WEBOPERATOR_API_TOKEN=<YOUR_WEBOPERATOR_API_TOKEN>' -- npx -y weboperator-mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.weboperator]
command = "npx"
args = ["-y", "weboperator-mcp"]

[mcp_servers.weboperator.env]
WEBOPERATOR_API_TOKEN = "<YOUR_WEBOPERATOR_API_TOKEN>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'WEBOPERATOR_API_TOKEN=<YOUR_WEBOPERATOR_API_TOKEN>' weboperator npx -- -y weboperator-mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "weboperator": {
      "command": "npx",
      "args": [
        "-y",
        "weboperator-mcp"
      ],
      "env": {
        "WEBOPERATOR_API_TOKEN": "<YOUR_WEBOPERATOR_API_TOKEN>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `WEBOPERATOR_API_TOKEN` | no | yes | Shared token required by the bridge when unauthenticated access is disabled. |
| `WEBOPERATOR_AGENT_SOCKET` | no | no | Unix socket path the bridge listens on. |
| `WEBOPERATOR_BRIDGE_PORT` | no | no | Port of the local WebOperator bridge HTTP API. |

## Tools (10)

- `browser_snapshot`: Capture the structured accessibility tree and numbered interactive elements (buttons, inputs, links) from the current active browser tab.
- `browser_navigate`: Navigate the active browser tab to a specified URL.
- `browser_click`: Click an element on the webpage by its numeric index (from browser_snapshot) or CSS selector.
- `browser_type`: Type text into an input field by element index or selector.
- `browser_press`: Press a keyboard key on the active webpage (e.g. "Enter", "Tab", "Escape", "ArrowDown", "Backspace").
- `browser_scroll`: Scroll the active webpage up or down.
- `browser_screenshot`: Capture a visual PNG screenshot of the current active browser tab.
- `browser_extract`: Extract text or structured data from the webpage according to an extraction instruction.
- `browser_solve_captcha`: Attempt to detect and automatically solve or click Cloudflare Turnstile, reCAPTCHA, or hCaptcha verification challenges in the active tab.
- `weboperator_execute_goal`: Execute an autonomous browser goal end-to-end using WebOperator multi-step planner.

## FAQ

### Does WebOperator use my existing browser sessions?

Yes, it works with the tabs you already have open, meaning your sessions and logins remain intact without needing to copy cookies or re-login.

### What tools are exposed via the MCP server?

The MCP bridge exposes ten tools including browser snapshot, navigate, click, type, press, scroll, screenshot, extract, solve captcha, and execute goal.

### Can I schedule recurring browser tasks?

Yes, you can schedule tasks with a start URL, a goal, and a cadence of once, hourly, daily, or weekly.
