# Search Scrape (SearXNG)

> Use this tool when you need to perform private and efficient web searches across multiple engines, and extract clean text from web pages for AI applications. It solves problems of unreliable web research and privacy concerns by providing a self-hosted, containerized solution with advanced content extraction capabilities. With inputs of search queries and URLs, it outputs extracted text and metadata, making it ideal for use cases where privacy and data control are crucial.

Canonical page: https://skillsregistry.net/skills/devshero-search-scrape  
JSON: https://api.skillsregistry.net/v1/skills/devshero-search-scrape

## Description

Pure Rust web search and scraping MCP server that combines SearXNG federated search with advanced content extraction capabilities. The implementation uses a containerized SearXNG instance for privacy-focused search across multiple engines (Google, DuckDuckGo, Bing, Startpage) while providing a sophisticated Rust-native scraper that leverages readability algorithms, language detection, and content preprocessing to extract clean text from web pages. Features comprehensive caching with Moka, concurrent request limiting, retry logic with exponential backoff, and specialized extraction for documentation sites like mdBook, making it valuable for AI applications that need reliable web research capabilities without depending on external scraping services or compromising user privacy through direct search engine APIs.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/devshero-search-scrape)
- **Repository:** <https://github.com/cortex-works/cortex-scout>

## 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": "devshero-search-scrape"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/devshero-search-scrape` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/devshero-search-scrape/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