MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
scraping-bee-mcpgithub.com/yourusername/scraping-bee-mcpupdated this year
ScrapingBee MCP server for testing web scraping extract rules
npm MIT -
—
★ 1 -
—
★ 1 -
scraping-mcp-servergithub.com/Readify-App/scraping-mcp-serverupdated this year
—
-
示例 MCP 服务器及将 Anthropic LLM 连接到外部网页爬虫工具的说明,包含真实应用示例和 Bright Data 集成。
-
MCP server for scrape-sdk — full-page scrape, search, extraction, and optional goal-based web agents with provider failover.
npm MIT -
high-performance-osint-scraping-mcpgithub.com/Fearlessversee/high-performance-osint-scraping-mcpactive
High-throughput asynchronous web intelligence scraping engine
NOASSERTION -
mcp-scrapeactive
反爬感知抓取 + 极省 Token 内容精简的 MCP Server
pypi MIT -
MCP Server for Puppeteer Scrapper
★ 1 -
x402-scrape-mcpactive
Web scraping MCP. Activate: npx x402-scrape-mcp --x402 https://scrape-toll-production.up.railway.app
npm -
realtimex-web-scraping-mcp-serverupdated this year
A Model Context Protocol (MCP) server for web scraping using Crawl4AI
pypi MIT -
Web Scraping Agent with N8N and MCP Server
★ 1 -
Example MCP server and instructions for connecting Anthropic LLMs to external web scraping tools, with real-world examples and Bright Data integration.
★ 5 -
search-scrape-supabase-ragdocsgithub.com/shariqriazz/search-scrape-supabase-ragdocsupdated this year
MCP server combining web search, scraping, Supabase management, and local documentation RAG tools.
-
iflow-mcp_thewebscrapingclub-ai-cursor-scraping-assistantgithub.com/thewebscrapingclub/ai-cursor-scraping-assistantupdated this year
AI-powered Cursor assistant for web scraping using MCP protocol
pypi mit -
scrape-do-mcpgithub.com/dztabel-happy/scrape-do-mcpupdated this year
MCP Server for Scrape.do - scraping, Google Search, Amazon, Async API, and Proxy Mode helpers
npm MIT -
An MCP server for (free!) search results via duckduckgo
★ 1 -
web-scraping-with-mcpgithub.com/bright-data-de/web-scraping-with-mcpupdated this year
Beispiel-MCP-Server und Anleitungen zum Verbinden von Anthropic LLMs mit externen Web-Scraping-Tools, mit praxisnahen Beispielen und Bright Data-Integration.
-
MCP server for ScrapingBot: let Claude, Cursor and other AI agents scrape web pages, products, real estate, travel, search engines and social media.
npm MIT -
Analyse robots.txt content and report whether a path may be crawled.
npm MIT -
Give Claude live web access via MCP: scrape pages, run Google searches and crawl sites from the chat.
MIT ★ 1 -
Public web page content as readable text or HTML for AI agents, powered by GeoRanker.
npm MIT -
MCP Server for Incredibly High Performant web scraper (seconds for what takes others lots of minutes) - battle tested on millions of websites.
MIT ★ 1 -
MCP server and command-line tool (scrapely) for the Scrapely Twitter/X DM Automation API — manage campaigns, scrape leads, send DMs, and more through Claude, any MCP client, or your terminal.
npm MIT -
scrape-mcpgithub.com/kadirharmanc/scrape-mcpupdated this year
Open-source MCP server for web scraping. Hybrid engine: lightweight (fetch+Cheerio) with automatic Playwright fallback. Zero config, no API keys needed.
npm MIT -
Scrape any website with Claude Code or Codex: Scrape.do MCP server, anti-bot playbook (Cloudflare, DataDome, Akamai) and self-healing scrapers that fix themselves when the site changes.
MIT -
A powerful tool that leverages Cursor AI and MCP (Model Context Protocol) to easily generate web scrapers for various types of websites.
MIT ★ 7 -
Serper Search and Scrapeno update data
Enable powerful web search and content extraction capabilities. Perform web searches and scrape webpage content seamlessly to enhance your applications with real-time data.
smithery -
Web scraping CLI and MCP server that turns any page into clean markdown — runs locally, or deploys to Cloudflare Workers in one command for use inside Claude and Codex sessions.
-
Anti-bot web scraper returning token-optimized Markdown for AI agents ($0.002 USDC on Base).
-
Firecrawl Web Scraping Serverno update data
Enable advanced web scraping, crawling, and content extraction capabilities for your agents. Perform deep research, batch scraping, and structured data extraction with automatic retries and rate limiting. Support both cloud and self-hosted deployments with seamless integration into popular MCP clients.
smithery -
Serper Search and Scrapeno update data
Habilite recursos poderosos de pesquisa na web e extração de conteúdo. Realize pesquisas ricas na web e raspe o conteúdo da página da web perfeitamente com a integração da API Serper.
smithery -
Analyze and ask questions about an input website using this Cloudflare MCP server
★ 6 -
URL → RAG-ready Markdown in one API call: heading-aligned chunks, embeddings, change-aware re-indexing, docs crawler + llms.txt, MCP server. Free tier.
-
AI Scraping Stack — web intelligence platform for competitor analysis & automated scraping. Multi-agent pipeline extracts insights from URLs, analyzes screenshots with VLMs, generates production-ready HTML/React code. 10+ providers with cascade fallback, zero-cost mode with Ollama + OpenRouter. Built with FastAPI, Pydantic, MCP
MIT -
📊 Automate job listing extraction from LinkedIn to streamline your research and recruitment efforts with efficient, bulk data collection.
★ 1 -
Firecrawl Web Scraping Serverno update data
Enable advanced web scraping, crawling, and content extraction with support for JavaScript rendering, batch processing, and smart filtering. Perform deep research and structured data extraction using LLM-powered tools. Monitor credit usage and handle rate limits automatically for efficient and reliable web data integration.
smithery -
MCP server for Google Search via pure scraping (no API key): HTTP fast path with cookie bootstrap, Camoufox browser fallback, proxy pool, adaptive cooldowns, forensics.
MIT -
URL to clean Markdown for AI agents. 2 tools: scrape_url (one page) and crawl_website (whole site). Blocked or paywalled pages are reported honestly, never invented. Hosted endpoint at scrape.mcp.goaimoat.com/mcp, free 3 calls per email, no card. A cheaper Firecrawl alternative; also runs locally via Docker.
MIT -
15 production data, monitoring and audit APIs on Apify — MCP-ready, pay-per-event, x402/USDC, 30 public task examples with verified outputs
★ 2 -
mcp-web-scrapegithub.com/mukul975/mcp-web-scrapeupdated this year
🚀 mcp-web-scrape — Clean, cache-aware web content fetcher for AI agents. Fetch any URL → extract readable content → return Markdown/JSON with citations. ⚡ Fast caching, 🤝 robots.txt compliant, 📝 Markdown-ready output, �� works with ChatGPT/Claude Desktop.
npm MIT ★ 50 -
diogenes-web-scraping-engine-mcpgithub.com/stand-out-of-my-sun/diogenes-web-scraping-engine-mcpactive
12 high-performance web extraction, readability & markdown tools: clean LLM markdown compiler, readable article extractor, OpenGraph & JSON-LD metadata parser, HTML table to JSON/Markdown converter, CSS selector isolator, paywall & overlay bypass auditor, XML sitemap crawler, hyperlink extractor, HTML XSS sanitizer, contact & lead info pa
MIT -
Official Model Context Protocol server (sdo-mcp) for the Scrape.do web scraping API
Apache-2.0 -
Official command-line client (sdo) for the Scrape.do web scraping API, with a bundled MCP server
Apache-2.0 -
openclaw-scraper-mcpupdated this year
MCP server for OpenClaw Web Scraping API — scrape URLs, extract structured data, batch scrape. Paid via x402 on Base mainnet.
npm MIT -
@octivas/mcpgithub.com/octivas/octivas-mcpupdated this year
MCP server for Octivas web scraping, crawling, and search API
npm MIT -
Tiny round-robin crawl MCP backed by Firecrawl, Tavily, and Scrape.do
npm MIT -
Scraping agent: routes each URL or query to the cheapest source that works and checks the result
MIT ★ 1 -
dataimpulse-scrapergithub.com/sonnysangha/dataimpulse-scraperupdated this year
MCP server for web scraping via DataImpulse residential proxies with per-request country targeting
pypi MIT -
Typed web scraping SDK — scrape, map, crawl, and search over HTTP, with a pluggable renderer, CLI, and MCP server
npm MIT -
@zapfetchdev/mcp-servergithub.com/zapfetch/mcpupdated this year
MCP server for ZapFetch - APAC-native web scraping API for AI agents
npm MIT -
@groundcraft/crawlgithub.com/humphreytheodore/groundcraftupdated this year
Groundcraft Crawl — scrape, search, map and crawl the web through one metered API. CLI, SDK and MCP server.
npm MIT -
sessemi-mcpgithub.com/sessemi/sessemi-mcpupdated this year
MCP server for Sessemi — scrape anti-bot protected sites from AI agents
pypi MIT -
Compare web scraping, crawling and SERP API pricing and limits against your workload and budget
-
MCP server for HTML scraping and data extraction using Puppeteer
npm MIT -
Stealth web scraping API for AI agents — native MCP integration, x402 micropayments, anti-bot bypass. Returns clean Markdown from any URL.
MIT ★ 1 -
Web scraping for Claude Desktop, Codex, and Gemini using Scrapedo API. Simple setup with npx.
npm MIT -
whizoai-mcpgithub.com/whizoai/whizoai-mcp-serverupdated this year
WhizoAI MCP Server for Claude Desktop - Enterprise web scraping through Model Context Protocol (MCP) integration
npm MIT -
mcp-researchpowerpackgithub.com/yigitkonur/mcp-researchpowerpackupdated this year
HTTP-first MCP research server: start-research plus raw/smart search and scrape tools — built on mcp-use.
npm MIT -
bypassapi-mcpgithub.com/inside83/bypassapi-mcpupdated this year
MCP server for web scraping + Cloudflare/CAPTCHA bypass — give your AI agent real web access. Works with Claude Desktop, Cursor, Windsurf, Cline.
MIT