# scrapy-mcp

> scrapy-mcp — musoukun-scrapy-mcp. Use this tool when you need to scrape websites with complex structures, from basic HTTP scraping to dynamic sites requiring JavaScript execution. It solves problems of data extraction from various web pages, handling different types of content and site architectures. The tool accepts website URLs as input and outputs scraped data, ideal for use cases involving web data mining and automation, particularly in projects managed with git.

Canonical page: https://skillsregistry.net/skills/musoukun-scrapy-mcp  
JSON: https://api.skillsregistry.net/v1/skills/musoukun-scrapy-mcp

## Description

MCPで基本的なHTTPスクレイピングから、JavaScript実行が必要な動的サイトまで対応した、TypeScript製のスクレイピングツールです。

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/musoukun/scrapy-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "musoukun-scrapy-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/musoukun-scrapy-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/musoukun-scrapy-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt