{"name":"io.github.SanggonBoy/PyreCrawl","slug":"sanggonboy-pyrecrawl","title":"PyreCrawl","description":"Web scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.","url":"https://mcp.market/server/sanggonboy-pyrecrawl","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"scraping","tags":["scraping"],"presence":{"score":39,"stars":18,"forks":1,"downloads_week":46,"last_push_at":"2026-09-21T15:57:41.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/SanggonBoy/PyreCrawl","website":"https://pypi.org/project/pyrecrawl/","version":"0.8.1","remotes":[],"packages":[{"registryType":"pypi","identifier":"pyrecrawl","version":"0.8.1","runtimeHint":"uvx","transport":{"type":"stdio"},"packageArguments":[{"type":"positional","valueHint":"serve"}]}],"tools":[{"name":"batch_scrape","description":"Scrape MANY URLs in ONE call (parallel, deduped, cache-aware).","write_action":false,"price_micros":0,"input_schema":null},{"name":"cache","description":"Inspect the response cache: stats, clear, enable, or disable.","write_action":false,"price_micros":0,"input_schema":null},{"name":"crawl","description":"Multi-page crawl: discover URLs on `root`, then scrape each.","write_action":false,"price_micros":0,"input_schema":null},{"name":"deep_research","description":"Search the web, then pull the top sources as EVIDENCE (no LLM synthesis).","write_action":false,"price_micros":0,"input_schema":null},{"name":"document","description":"Extract text from a PDF/DOCX/PPTX URL → markdown (no browser).","write_action":false,"price_micros":0,"input_schema":null},{"name":"extract","description":"Scrape + structured extraction using a CSS-based JSON schema.","write_action":false,"price_micros":0,"input_schema":null},{"name":"health","description":"Verify PyreCrawl is working: engine versions, dependencies, update status.","write_action":false,"price_micros":0,"input_schema":null},{"name":"map_site","description":"Enumerate all internal URLs reachable from `root`.","write_action":false,"price_micros":0,"input_schema":null},{"name":"monitor","description":"Track a URL over time and report meaningful content changes.","write_action":false,"price_micros":0,"input_schema":null},{"name":"scrape","description":"Scrape a single URL → LLM-ready markdown.","write_action":false,"price_micros":0,"input_schema":null},{"name":"search","description":"Web search via DuckDuckGo HTML (no API key required).","write_action":false,"price_micros":0,"input_schema":null},{"name":"search_papers","description":"Search academic papers via arXiv or Crossref — no API keys.","write_action":false,"price_micros":0,"input_schema":null},{"name":"session","description":"Drive a persistent browser session — cookies & JS state kept across calls.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-10-02T22:41:18.170Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-10-02T22:41:18.176Z","components":{"code":{"score":25,"max":25,"notes":["10 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 11 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"pypi","identifier":"pyrecrawl","version":"0.8.1","found":true,"weeklyDownloads":46,"license":"MIT","dependencyCount":10,"publishedAt":"2026-09-21T19:10:12.124948Z","repositoryUrl":"https://github.com/SanggonBoy/PyreCrawl"}],"repo":{"found":true,"owner":"SanggonBoy","repo":"PyreCrawl","archived":false,"pushedAt":"2026-09-21T15:57:41Z","stars":18,"forks":1,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/118122698?v=4","ownerCreatedAt":"2022-11-13T16:02:22Z","license":"MIT"},"icon":{"url":"https://avatars.githubusercontent.com/u/118122698?v=4&s=128","source":"registry","width":128,"height":128},"presence":{"stars":18,"forks":1,"downloadsWeek":46,"license":"MIT","lastPushAt":"2026-09-21T15:57:41.000Z","score":39}}}},"grade_history":[],"reviews":[]}