搜索「Web Scraping」的结果

io.github.genclass-dev/genclass

Find race conditions in your web app by reordering its responses, replay one, prove the fix.

io.github.Mingye-Lu/acrawl

自主网页爬虫：17 个浏览器工具，外加目标驱动的 run_goal 智能体；单二进制、隐身模式。

io.github.firecrawl/firecrawl-mcp-server

Firecrawl 的 MCP server——网页搜索、网页抓取，以及生物医学/arXiv 论文检索。

com.arettic/arettic

One key for agent data tools: emails, companies, search, scraping. Pay only for results that pass.

io.github.Ynewtime/markitai

Convert documents, images and web pages to clean Markdown, for agents: single, URL and batch tools.

io.github.Kumar2421/marlo-mcp

Audit a web page for SEO and technical issues with Marlo, the open-source AI CMO. Read-only.

io.github.perzianhq/mantis

The web as short, numbered text for AI agents: a lean browser interface over Playwright.

io.github.LastSearch-HQ/lastsearch

Evidence-backed web research for AI agents with citations and confidence scores.

io.github.cyanheads/browser-compat-mcp-server

Browser compatibility and Baseline status for any web feature — offline, from bundled MDN data.

io.github.crawlbrulee/mcp

EU-native web scraping for AI agents. scrape pages, map sites, run background jobs, check usage.

com.conv2pdf/conv2pdf

Convert Office files, images, e-books and web pages to PDF; merge, split, compress or protect PDFs.

io.github.dmytrome/groundhog-mcp

搜索、阅读并调研网页，默认剥离隐藏文本，并对来源做哈希。

io.github.ellmos-ai/ellmos-filecommander-mcp

Filesystem MCP server: files, previews, search, processes, OCR, archives, safe delete, web fetch.

dev.true402/mcp-server

通过 x402（Base 上的 USDC）按次调用的 AI + Web + 链上工具：LLM、SEO、抽取、代币安全。

io.github.honestkit/honestkit-mcp

18 web-data tools (WHOIS/DNS/SSL, SEO, Wayback, App Store ranks, BR/FR company data) via Apify.

io.github.Role1776/mcp-retrieval

Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown.

io.github.martinPisacreta/textokit-mcp

17 pay-per-call x402 tools on Base: web reader, FX/crypto rates, Argentine data. Remote or npx.

io.github.sbd530/page-scanner

Capture a web page from your own Chrome as a PDF whose text is still text.

io.github.raintree-technology/docpull

把公开网页来源同步为带引用出处的上下文包，供 AI 智能体、RAG 与 MCP 客户端使用。

io.github.Rererr/amenbo

Japanese-web-native MCP server for low-impact, token-efficient web collection

io.github.zraisan/deputy

Any web page as a typed tool call, run in your own logged-in Chrome. Free to start; Pro adds more.

com.htmlradar/share

将 HTML 发布为带追踪的链接，查看谁打开过以及读了哪些章节。

ai.neuralverge/neuralverge

Structured, cited, real-world data from 300+ sources and the open web for your AI agents.

io.github.feder-cr/invisible-playwright-mcp

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.