# webharvest

> webharvest — dan-rozhkov-webharvest. Use this tool when you need to extract data from websites while respecting courtesy rate limits and leveraging caching for efficient web scraping. It solves problems related to web data extraction, search, and monitoring by providing a localized solution. The tool accepts website URLs and search queries as inputs and outputs scraped data, making it ideal for use cases requiring targeted web data collection.

Canonical page: https://skillsregistry.net/skills/dan-rozhkov-webharvest  
JSON: https://api.skillsregistry.net/v1/skills/dan-rozhkov-webharvest

## Description

Enables web search and scraping through MCP, running locally with courtesy rate limiting and caching.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jppq78k6mg)
- **Repository:** <https://github.com/dan-rozhkov/webharvest>

## 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": "dan-rozhkov-webharvest"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dan-rozhkov-webharvest` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dan-rozhkov-webharvest/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