# SnoopScan

Converts web pages into clean Markdown or structured JSON inside an AI agent session. Useful for crawling sites, bypassing blocks, and parsing documents.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: SnoopScan
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/SnoopScan/snoopscan-core
- Updated: 2026-10-12
- HTML: https://affpapa.org/en/nevibecode/mcp/snoopscan

## What it does

SnoopScan equips your assistant with web scraping and site crawling. It transforms messy web pages into readable Markdown, extracts data into defined JSON schemas, and converts PDF, DOCX, or XLSX files into text. Every endpoint acts as an MCP tool.

The open-source core processes requests strictly over plain HTTP. When a target page requires browser JavaScript execution, the local server returns a `BLOCKED` status instead of partial content. Bypassing bot protections and running headless browsers requires the hosted service, which provides 1500 free credits monthly.

To safeguard your model context, each content tool accepts a `maxChars` limit and outputs continuation tokens when truncated. If you connect to the remote endpoint without an API key, access is capped at 20 free calls daily per IP address for basic scraping and search.

## Requirements
- Remote server: `https://api.snoopscan.com/mcp-oauth`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http snoopscan https://api.snoopscan.com/mcp-oauth
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add snoopscan --url https://api.snoopscan.com/mcp-oauth
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "snoopscan": {
            "url": "https://api.snoopscan.com/mcp-oauth"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "snoopscan": {
            "type": "http",
            "url": "https://api.snoopscan.com/mcp-oauth"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http snoopscan https://api.snoopscan.com/mcp-oauth
```

## When to use it
- Scrape a public URL into clean Markdown for immediate analysis
- Map all URLs on a target domain ordered by relevance
- Extract structured data from web pages into a JSON schema
- Convert PDF, XLSX, or DOCX documents into Markdown text

## Example prompts
- Scrape `https://example.com/` and output the content in clean Markdown
- Map all URLs on `https://example.com/` by relevance
- Extract structured page data from `https://example.com/` as JSON

## 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