Home › Search & Research › searxNcrawl

searxNcrawl

Web search via SearXNG and/or You.com, plus clean Markdown crawling via Crawl4AI. Self-hosted.

Python

★ 167 stars Last pushed 2026-10-16 License: MIT

View repository → Website →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (pypi 0.32.0)

uvx searxncrawl

Or add to your MCP client config:

{
  "mcpServers": {
    "searxncrawl": {
      "command": "uvx",
      "args": [
        "searxncrawl"
      ],
      "env": {
        "SEARXNG_URL": "<YOUR_VALUE>",
        "SEARXNG_USERNAME": "<YOUR_VALUE>",
        "SEARXNG_PASSWORD": "<YOUR_VALUE>",
        "YDC_API_KEY": "<YOUR_VALUE>",
        "SEARCH_RESULT_FIELDS": "<YOUR_VALUE>"
      }
    }
  }
}

SEARXNG_URL — URL of your SearXNG instance with JSON output enabled; enables SearXNG search (no default)
SEARXNG_USERNAME — Optional basic auth user for SearXNG (set both or neither)
SEARXNG_PASSWORD secret — Optional basic auth password for SearXNG (set both or neither)
YDC_API_KEY secret — You.com API key; enables You.com search (queries go to You.com, US)
SEARCH_RESULT_FIELDS — Comma-separated result fields: title,url,content,publishedDate,providers (unset = all)