# cdpilot

cdpilot lets an AI agent control a browser through CDP. Use it to navigate pages, interact with elements, and capture screenshots.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 32
- Author: mehmetnadir
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mehmetnadir/cdpilot
- Updated: 2026-10-16
- HTML: https://affpapa.org/en/nevibecode/mcp/cdpilot

## What it does

The server gives an agent commands to open pages, click controls, enter text, and take screenshots in a separate browser profile. It also offers tools for inspecting network activity, console output, and accessibility. Browser control uses CDP rather than Puppeteer, Playwright, or Selenium.

You need Node.js 18+, Python 3.10+, and Brave Browser, Google Chrome, or Chromium. A preflight wizard installs Python’s `websockets` module on the first launch. Automation runs locally in an isolated profile, so a supported browser must be available to start a session.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add cdpilot -- npx -y cdpilot
```

### Codex

**Platform CLI**
```bash
codex mcp add cdpilot -- npx -y cdpilot
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cdpilot": {
            "command": "npx",
            "args": [
                "-y",
                "cdpilot"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cdpilot": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "cdpilot"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add cdpilot npx -y cdpilot
```

## When to use it
- open a page in an isolated browser profile
- click a page element and fill in a form
- capture a screenshot after navigation
- inspect console output and network requests

## Example prompts
- Open `https://example.com` and take a screenshot.
- Go to the sign-in page, fill in the form, and submit it.
- Inspect network requests and console output after the page loads.

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md