Siftdog
io.github.khsarvar/siftdog
Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.
Connect this server
Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.
{
"mcpServers": {
"siftdog": {
"command": "uvx",
"args": [
"siftdog"
]
}
}
}A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Search & Web
- Version
- 0.3.0
- Registry
- active
- Published
- 9/28/2026
More Search & Web servers
Browse all Search & Web →Kreuzcrawl
kreuzberg-dev
Scrape, crawl, and map websites to Markdown or JSON via local CLI.
Google Play Store
kryuchenko
Read-only Google Play data: app details, search, charts, reviews, permissions, data safety
Google News
lewisdonovan
Search Google News, get top stories and read articles. No API key or headless browser.
TheCrawler
manchittlab
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
DeepSeek Web Search
Matthewyin
MCP server for DeepSeek web Search & Fetch: scored web search + page-to-Markdown fetch
io.github.MetaLift-AI/metalift
MetaLift-AI
Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools
Add the badge to your site
Show visitors that Siftdog is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-khsarvar-siftdog?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Siftdog — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-khsarvar-siftdog?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.