# Wick

A local MCP server that bypasses anti-bot defenses using Chrome's networking pipeline. It returns scraped pages as markdown straight to your AI agent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9
- Author: wickproject
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/wickproject/wick
- Updated: 2026-08-08
- HTML: https://affpapa.org/en/nevibecode/mcp/wick

## What it does

Standard HTTP libraries in Python or Node give away their identity during the TLS handshake. Bot protection systems spot those signatures immediately. Wick takes a different path. It runs Chrome's internal Cronet and BoringSSL stack locally, keeping your residential IP while presenting a genuine browser fingerprint.

The server packages tools for single-page retrieval, site crawling, sitemap mapping, and web searches. Content arrives formatted as markdown, though raw HTML or text remains available. It can also grab video or audio streams through an integrated yt-dlp tool.

Keep the engine tiers in mind. Full JavaScript execution requires the paid Pro version with patched Chromium, so the free build relies strictly on static network responses.

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

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- bypass anti-bot barriers like Cloudflare or Akamai during web scraping
- fetch clean markdown representations of web pages for agent context
- crawl websites and map URL structures automatically
- download audio and video files from supported platforms via yt-dlp

## Example prompts
- Fetch `https://www.nytimes.com` using the `wick_fetch` tool and display it in markdown.
- Crawl `https://docs.example.com` with `wick_crawl` up to depth 2 and summarize the articles.
- Map all internal URLs on `https://example.com` using `wick_map` with a limit of 50 links.

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32260
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13181
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 13345

---
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