Hound MCP adds web search, crawling, and PDF reading to agents
Hound V9 is a free that runs on your own computer. It lets an AI agent search the web, fetch web pages, crawl sites, get past some Cloudflare blocks, read PDFs, and extract text from .
It does not require an account, an API key, or paid search services, and it is released under the . Search uses several sources, including DuckDuckGo, Brave, Google, Startpage, Qwant, and Wikipedia, then uses a local ONNX model to reorder results.
Page fetching uses a Patchright browser setup aimed at pages that block normal with Cloudflare security checks. Crawling can follow important pages first, use a sitemap-style mode to map a site in one call, and set limits for page count, crawl depth, and character count.
Key points
- Hound V9 as a free .
- It combines , page fetching, crawling, PDF reading, and scanned-PDF text extraction.
- It is designed to work without accounts, API keys, or paid search APIs.
- It can use several search sources and rerank results locally with ONNX.
- Crawls can be limited by page count, depth, and character budget.