{"name":"io.github.waiky-github/CrawlEyes","slug":"waiky-github-crawleyes","title":"CrawlEyes MCP Server","description":"Web scraping & search for AI agents: extract, SearXNG search, rerank, robots compliance. No API key.","url":"https://mcp.market/server/waiky-github-crawleyes","rating":null,"grade":"B","score":83,"certified":false,"status":"active","category":"scraping","tags":["scraping","search"],"presence":{"score":30,"stars":2,"forks":0,"downloads_week":30,"last_push_at":"2026-09-09T14:53:12.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/waiky-github/CrawlEyes","website":"https://github.com/waiky-github/CrawlEyes","version":"0.2.0","remotes":[],"packages":[{"registryType":"pypi","identifier":"crawleyes","version":"0.2.0","transport":{"type":"stdio"},"environmentVariables":[{"description":"Optional. Base URL of a SearXNG instance (e.g. http://localhost:8080). If unset, falls back to Tavily keyless.","format":"string","name":"SEARXNG_URL"},{"description":"Optional. Tavily API key for higher-rate search fallback. If unset, uses Tavily keyless (rate-limited).","format":"string","isSecret":true,"name":"TAVILY_API_KEY"}]}],"tools":[{"name":"deep_research","description":"深度调研：把主题拆成子问题→搜索→抓取→合成带引用的报告。 Uses SearXNG → Tavily keyless (no API key). Optional LLM synthesis via CRAWLEYES_LLM_* env vars; without them returns an evidence-aggregate report. Returns JSON with report (Markdown) + sources.","write_action":false,"price_micros":0,"input_schema":null},{"name":"extract","description":"抓取网页正文为 Markdown。自动去噪（过滤导航/广告），失败自动重试。 返回前会剥离隐藏文字 + 标记可疑注入，防止 prompt-injection 劫持 Agent。 respect_robots=True 时先检查目标站 robots.txt (RFC 9309)，被 Disallow 则拒绝。 format: markdown(默认) | fit | raw | markdown_with_citations。 Returns JSON with title/markdown/length.","write_action":false,"price_micros":0,"input_schema":null},{"name":"search","description":"搜索网页。SearXNG 优先，失败自动 fallback Tavily keyless（无需 API key）。 带统一限流 + 指数退避重试（最多 3 次）。 limit 会被 clamp 到 [1, 20]，防止传超大值打爆下游。 Returns JSON with title/url/description for each result.","write_action":false,"price_micros":0,"input_schema":null},{"name":"sitemap","description":"发现站点 URL 地图。解析 {origin}/sitemap.xml（支持 index/gzip）， 缺失时回退 robots.txt 的 Sitemap 声明。返回去重后的 URL 列表 JSON。 用于整站抓取 / deep_research 扩 URL 源。带统一限流。","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":83,"grade":"B","scanned_at":"2026-09-20T20:11:19.307Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-20T20:11:19.175Z","components":{"code":{"score":25,"max":25,"notes":["12 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":6,"max":15,"notes":["static API keys via environment variables"]},"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":"crawleyes","version":"0.2.0","found":true,"weeklyDownloads":30,"license":"MIT","dependencyCount":9,"publishedAt":"2026-09-01T16:00:00.632293Z"}],"repo":{"found":true,"owner":"waiky-github","repo":"CrawlEyes","archived":false,"pushedAt":"2026-09-09T14:53:12Z","stars":2,"forks":0,"openIssues":0,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/55820677?v=4","ownerCreatedAt":"2019-09-26T02:31:27Z","license":"MIT"},"icon":{"url":"https://raw.githubusercontent.com/waiky-github/CrawlEyes/main/assets/icon.png","source":"registry","width":512,"height":512},"presence":{"stars":2,"forks":0,"downloadsWeek":30,"license":"MIT","lastPushAt":"2026-09-09T14:53:12.000Z","score":30}}}},"grade_history":[],"reviews":[]}