toolforte
v1.11.0
Exact IBAN, VAT, cron, regex answers; HTML/URL to hosted PDF or screenshot; agent memory; workflows.
使用场景/网页抓取与采集
从网页提取结构化内容、爬取文档、监控变更。适合调研、内容聚合、知识库构建。
共匹配 889 个资源 · 第 12 / 19 页
网页抓取类 MCP Server 把互联网内容变成 AI 可直接消费的结构化文本:Firecrawl 类服务负责整站爬取与 Markdown 转换,Fetch 类服务负责单页拉取与重定向处理。相比浏览器自动化,它们不渲染交互、速度快、token 消耗低,是构建 RAG 语料与知识库的首选采集层。
典型工作流:用 Firecrawl MCP 批量爬取文档站 → 清洗为 Markdown → 送入向量库(如 Qdrant / Chroma MCP)→ 再用检索 MCP 让 AI 基于自有语料回答。AgentHub 上每个抓取类资源都附带安装命令与客户端配置,可直接复制到 Cursor 或 Claude Code。
合规边界:只抓取公开页面,遵守目标站点 robots.txt 与服务条款;控制并发与频率,避免给对方服务造成压力;需要登录才能访问的内容不要自动化批量拉取。
v1.11.0
Exact IBAN, VAT, cron, regex answers; HTML/URL to hosted PDF or screenshot; agent memory; workflows.
v0.1.0
Web search and clean-text fetch MCP server (Tavily-powered, SSRF-guarded).
v1.0.0
Tor gateway for AI agents: fetch URLs and rotate circuits through Tor, Bitcoin-settled.
v0.1.5
Audits HTML, JSX, Vue, Twig, Blade, ERB and Razor markup against the 24 WCAG 2.1 Level AA checks tha
v3.6.0
Zero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
v1.1.0
Search and fetch AI agent skills, rules files and MCP servers indexed from GitHub.
v1.0.4
Finds the lit-html binding positions auto-escaping does not cover, before the component ships
v1.7.0
Search agent-ready sites or fetch one site's report; every capability probe-verified, dated.
v1.0.4
Reads your HTML and Markdown product copy and flags the environmental claims Directive (EU) 2024/825
v1.0.1
同梱の54行の採用サイトHTML(外部送信タグ4本+GTMコンテナ1つ)で公表もれ6件を行番号つきで名指し。電気通信事業法27条の12(2023年6月16日施行)の公表4項目を15 checksで照合
v1.0.2
Finds unauthorised nutrition and health claims in your product-page HTML and Markdown and names the
v1.0.6
Fourteen checks on an HTML email footer: CAN-SPAM postal address and 10-business-day opt-out, CASL's
v1.0.0
Economic reports for 20 economies, 2015-2025. Search free, pay per fetch in USDC on Base via x402.
v1.0.0
Search and fetch genuine Icons8 icons and Ouch illustrations as SVG, PNG or animation.
v1.0.0
Neonix compiles HTML and CSS into a real, exportable motion video.
v1.30.2
面向 Web 应用的 AI 测试智能体——派发测试任务、执行爬取、获取产物与状态。
v0.1.1
160+ finished slide layouts and 41 themes your agent can search, fetch and build a deck from
v0.6.0
查找 NOAA 潮汐站与 NDBC 浮标,获取潮汐预报、海流与实时海况。
v0.4.1
对接 iNavi Maps API 的 MCP 服务器,为 Claude AI 提供地理编码、POI 检索与路径规划。
v0.1.8
检索 MusicBrainz 的艺人、发行、作品与厂牌,解析 ISRC/ISWC/条形码并获取封面图。
v1.0.0
Flipside Crypto SQL API: run queries, check status, fetch results.
v0.6.4
检索 NOAA 气候观测站与数据集,获取历史气象观测记录。
v0.2.3
把 HTML/Markdown 渲染为 PDF、将数据行导出为 xlsx,并填写 AcroForm 表单 PDF。
v1.0.0-draft.2
Verify signed AIFeed permissions, fetch token-budgeted markdown, and verify assets for AI agents.
v1.0.0
Agent utility API: 28+ free endpoints (hash, QR, DNS, scrape, JWT...) run by an autonomous AI agent.
v1.0.0
Search Wikipedia, fetch article summaries.
v1.0.0
Search the MDN web docs for HTML, CSS, and JavaScript. No key required.
v1.0.0
Convert markdown to HTML and extract headings locally. No network and no key.
v1.0.0
Search books and fetch volume details from the Google Books API. No key required.
v1.1.0
PDF, Word, PowerPoint, Excel, HTML, EPUB to Markdown: OCR, page ranges, tables, RAG chunking
v0.5.2-registry.1
Backlink monitoring with dated fetch evidence; checks and change events continue after the chat.
v0.3.1
Self-hosted SearXNG metasearch for MCP clients: web, image, news, video, music and page fetch.
v0.2.4
基于 UniProtKB 开展蛋白研究——按功能检索、获取精校记录、映射 ID 与蛋白质组。
v0.1.19
搜索并获取 Wikidata 实体、执行 SPARQL 查询、解析外部标识符。
v2.0.0
在 AI 智能体中由 HTML、URL 或模板生成图片、GIF、视频与 PDF。
v1.0.0
Turn HTML, Markdown, URLs and saved templates into PDFs with the PodPDF API.
v0.1.15
检索 Stack Exchange 问题,以 Markdown 获取问答讨论串,查询标签常见问题与用户资料。
v0.2.0-beta.3
48-hour HTTPS previews of prebuilt static sites and HTML slides. No server builds or backends.
v1.5.3
检索 arXiv 论文,获取论文元数据并读取全文内容。
v1.4.2
50 developer utility APIs as tools: SSL, DNS, WHOIS, email checks, HTML to PDF, sitemaps and more.
v0.1.0
Web scraping for AI agents: scrape, search, crawl, map any website to markdown + JSON. No browser.
v1.0.0
Put an HTML or React artifact online as a web page with its own address, password and stats.
v0.3.0
Paid tools for HTML, JSON, shopping data and agent configs. Free discovery; $5 prepaid credits.
v0.5.1
换算货币并获取来自 50 多个机构来源的综合汇率。
v0.1.0
Search and fetch skills from your org's Skills and Agents catalog. Bearer token required.
v0.1.4
Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved
v1.2.4
让 AI 智能体动态抓取并解析网页内容,包括地理受限站点。
v0.2.0
Publish HTML to a shareable link and collect feedback anchored to the passage it refers to.
静态或服务端渲染的页面、整站文档爬取用抓取类(Firecrawl/Fetch);需要点击、滚动、登录交互或抓渲染后截图,用浏览器自动化(Playwright MCP)。
托管版需要;也可以自部署开源版,或用免费的 Fetch MCP 做单页抓取。资源详情页会标注分发方式与所需环境变量。
常见做法是 Markdown 清洗后写入向量库 MCP(Qdrant、Chroma、pgvector 等),再配合检索 Skill 或 Context7 类知识库 MCP 完成问答。