搜索「Web Scraping」的结果

io.github.D4Vinci/Scrapling

网页抓取，支持隐蔽 HTTP、真实浏览器与 Cloudflare 绕过，支持 CSS 选择器。

ca.ohey/research

Web malware techniques, kits and EtherHiding contracts from Ohey's website scans. No sign-in.

io.github.PHONGUIT22/nostrpulse

Autonomous payment & Web-of-Trust anti-Sybil layer for AI agents via Nostr & Cashu (NIP-61 NutZaps).

io.github.pipeworx-io/oxylabs

Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)

app.vercel.clearpage-x402/clearpage

Web page to clean Markdown and metadata for agents. Free daily trial, then x402 USDC.

sh.metasearch/search

Web search and page reading: news, papers, people, patents and places, with sources and cost.

io.github.pipeworx-io/onet

O*NET MCP — wraps the O*NET Web Services (US DOL) occupation taxonomy.

io.github.pipeworx-io/nbp-pl

Narodowy Bank Polski（波兰国家银行）Web API MCP，无需 key。

io.github.pipeworx-io/musicbrainz

MusicBrainz MCP——封装 MusicBrainz Web Service v2（免费，无需鉴权）。

io.github.outcrawlai/outcrawl

Web infrastructure for AI agents: scrape, crawl and search the web, run browsers and agents.

io.iron-out/ux-benchmark

UX Score and Web Vitals (TTFB, FCP, LCP, INP, CLS) for any website, from real-user CrUX data.

io.github.CloudCorpRecords/channelchat

Slack channels, messages, threads, reactions and users via the Slack Web API.

io.github.pipeworx-io/epa-echo

EPA ECHO MCP，封装 EPA ECHO Web Services（免费、无需鉴权）。

io.github.radoxtech/deepseek-search-everywhere-mcp

Web search, page fetching and multi-source research via the DeepSeek Search & Fetch API.

io.github.pipeworx-io/decodo

Decodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly Smartproxy).

io.github.A1-x-Tech/mcp-google-crux

来自 Chrome UX Report（CrUX）API 的真实用户 Core Web Vitals，覆盖任意源站或 URL。

dev.workers.a-347.avocado-read-api/read

Web page to clean Markdown for agents. Pay per call ($0.003 USDC on Base) via x402.

app.singitai/singit

Web search, page reading, prices and market data for agents, billed to your SingIt API key in USDC.

io.github.CloudCorpRecords/researchsearch

Web search, page extraction, crawling, and site mapping powered by the Tavily API.

io.github.CloudCorpRecords/searchport

Web, local, news, image, and video search through the Brave Search API.

io.github.pipeworx-io/chrome-ux-report

Real-user Core Web Vitals for any website with enough traffic.

io.github.pipeworx-io/careeronestop

CareerOneStop MCP — wraps the CareerOneStop Web API (U.S.

io.github.pipeworx-io/bright-data

Bright Data MCP — Bright Data Web Unlocker + SERP API (brightdata.com)

io.github.CloudCorpRecords/privatesearch

Web search through DuckDuckGo and readable page fetching, no API key needed.