# Sleepwalker

MCP server that audits brand citations across AI search engines and serializes web pages to inspect structured data seen by crawlers.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 25
- Author: followanton
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/followanton/sleepwalker
- Updated: 2026-07-30
- HTML: https://affpapa.org/en/nevibecode/mcp/sleepwalker

## What it does

This tool connects your coding assistant to tracking pipelines across ChatGPT, Perplexity, Grok, and Gemini. It inspects whether models cite your site, monitors competitor presence, and tracks referenced domains in generated answers.

It also handles content serialization, converting public URLs into clean markdown and gathering crawler snapshots. The technical view captures JSON-LD blocks, meta tags, and robots directives exactly as served to bots that skip JavaScript execution.

Live visibility queries depend on a remote endpoint at `https://mcp.sleepwalker.ai/mcp` and require an account API token from `app.sleepwalker.ai`.

## Requirements
- Remote server: `https://mcp.sleepwalker.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http sleepwalker https://mcp.sleepwalker.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add sleepwalker --url https://mcp.sleepwalker.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "sleepwalker": {
            "url": "https://mcp.sleepwalker.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "sleepwalker": {
            "type": "http",
            "url": "https://mcp.sleepwalker.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http sleepwalker https://mcp.sleepwalker.ai/mcp
```

## When to use it
- inspect brand citations across Perplexity and ChatGPT
- audit JSON-LD and microdata visible to non-JavaScript crawlers
- monitor competitor visibility in AI search responses
- extract clean markdown bundles from web pages

## Example prompts
- Check how ChatGPT and Perplexity cite our brand for enterprise search queries
- Inspect the technical snapshot and robots directives for `https://www.sleepwalker.ai`
- Analyze competitor mentions across Gemini and Grok for visibility gaps

## Similar
- [New-Term Radar](https://affpapa.org/en/nevibecode/mcp/new-term-radar.md) — MCP server · ★ 1766
- [NotFair](https://affpapa.org/en/nevibecode/mcp/notfair.md) — MCP server · ★ 4055
- [seo-monster](https://affpapa.org/en/nevibecode/mcp/seo-monster.md) — MCP server · ★ 553
- [Google Maps MCP Server](https://affpapa.org/en/nevibecode/mcp/google-maps-mcp-server.md) — MCP server · ★ 479
- [Search Console MCP](https://affpapa.org/en/nevibecode/mcp/search-console-mcp.md) — MCP server · ★ 308
- [squirrelscan](https://affpapa.org/en/nevibecode/mcp/squirrelscan.md) — MCP server · ★ 296

---
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