MCP Tools DirectoryAbout this integration
13 tools for AI agents: scrape, crawl, extract, map, search, papers, batch, research, monitor.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.7.5
- Package
- pyrecrawl
- Last compatibility test
- Not independently tested
Connect your agent
pyrecrawlPublisher documentation was reviewed from pinned captures. The package was not executed, browser engines were not installed, and no site was fetched; publisher documentation also discloses an opt-out anonymous startup ping.
Capabilities: web scraping, structured extraction, site crawling, web and paper search, persistent browser sessions
Connected profiles
Additional details
io.github.SanggonBoy/PyreCrawl
Source ↗ · Checked 2026-09-170.7.5
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17pyrecrawl
Source ↗ · Checked 2026-09-190.8.0
Source ↗ · Checked 2026-09-19The documented MCP configurations run the pyrecrawl console executable in serve mode over stdio from the client.
Source ↗ · Checked 2026-09-19The publisher describes the self-hosted web tools as requiring no API key, while individual target sites may independently require sessions or login.
Source ↗ · Checked 2026-09-19The local server fetches operator-supplied URLs using an HTTP-to-browser fallback ladder and also connects to documented public search services.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19