# CRW Web Scraper

> Use this tool when you need to extract data from websites, crawl complex web structures, or map online information architectures. The CRW Web Scraper solves problems of data collection, research, and monitoring by providing a flexible and customizable scraping solution. It takes in website URLs and parameters as input and outputs structured data in various formats, making it ideal for AI agents requiring web data integration in their workflows.

Canonical page: https://skillsregistry.net/skills/io-github-us-crw  
JSON: https://api.skillsregistry.net/v1/skills/io-github-us-crw

## Description

Open-source web scraper for AI agents with scrape, crawl, and map tools

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.2.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-04-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.us%2Fcrw)
- **Repository:** <https://github.com/us/crw>

## 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": "io-github-us-crw"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-us-crw` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-us-crw/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