MCP server directory
53,271 MCP servers that connect AI assistants to tools and data, from the official MCP Registry and the community lists, updated every hour.
- 16 categories
- 33,674 remote servers
- Updated every hour
Hadacart KR/US product search and purchase linkscom.hadacart/catalog-snapshots
Search KR/US products, dated options and unit prices; original merchant affiliate purchase links.
ResearchCalcom.researchcal/researchcal
Conference and call for papers deadlines in economics, business and political science, with sources.
Shotlanedev.shotlane/shotlane
Screenshot web pages, read them as clean Markdown (JS rendered), and render HTML to PDF.
Ink Studio AIio.github.ciroartz/inkstudioai
Generate AI tattoo designs in 13 styles, search a public tattoo gallery, and check plans.
SerpKiteio.github.SerpKite/serpkite
Google search, news, maps, scholar, webpages, cited AI answers and deep research for AI agents.
Voidly Hosted MCPio.github.voidly-ai/voidly-hosted
Voidly MCP: research, Atlas score, capabilities; gated Voidpay, Voidmail, Home, board and bounty.
LupyAicom.lupyai/lupyai
Ask about your Meta Ads, Google Ads, GA4, Search Console, Shopify and other marketing data.
GSC Magiccom.gscmagic/gsc-magic
Google Search Console, Bing, GA4 and SEO reports for Claude, ChatGPT and any MCP client
Relvatocom.relvato/relvato
Website monitoring: uptime, checkout, SEO (Search Console, Bing), security, speed, DNS, compliance.
search-rotationio.github.robin-bially/search-rotation
MCP server for web search and page extraction across the free tiers of several providers
Tileiocom.tileio/tileio
Search 700+ design layers and fetch the build prompt for HTML, Next.js, React, Vue and more.
RecordHTMLcom.recordhtml/mcp
Record web pages and HTML5 creatives to MP4, WebM or GIF in a real browser.
Servo Fetchgithub.com/konippi/servo-fetch
Chromium-free web content extraction in a single binary: fetch, render, crawl and screenshot pages with the Servo browser engine.
Peerivo Watchio.github.Peerivo/watch
Web search, data extraction and controlled browser automation for AI assistants via OAuth.
Memorylanegithub.com/deusXmachina-dev/memorylane
Desktop app that captures screen activity, stores AI summaries and OCR text locally, and exposes the history via semantic search and a timeline.
Relaycom.relaygpu/mcp
Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.
ITASCA MCP Serverio.github.yusong652/itasca-mcp
MCP server for ITASCA PFC, FLAC3D, 3DEC, MPoint and MassFlow: search docs, run simulations, plot.
CitedByeu.citedby/citedby
Check a page, AI-crawler access, llms.txt and backlinks of a site. Free, read-only.
PinPinterest — Pinterest Keyword Researchcom.pinpinterest/keywords
Pinterest keyword research from our own crawl: saves, competition, related terms, trends, top pins.
Cotletdev.cotlet/cotlet
Cotlet's own tools: a cloud browser signed in as the user, account, credits and calls.
Transicadev.transica/transica
Checks whether a web page is ready for AI agents and whether an MCP server meets directory rules
PayAPI Marketmarket.payapi/marketplace
Search settlement-verified x402 APIs for free. Pay providers in USDC on Base, Solana or Algorand.
AgentReadio.github.omarhassanatef/agentread
Web pages to clean Markdown for AI agents. 5 free calls/day, then pay per call via x402 on Base.
인터넷트렌드 맛보기 (InternetTrend Try)kr.co.internettrend/internettrend-try
Try InternetTrend without login: Korean search, AI platform and browser shares for completed months.
인터넷트렌드 (InternetTrend)kr.co.internettrend/internettrend
Korean web usage stats from real site logs: search engine, AI platform, browser, OS by industry.
WHOISio.github.KincaidYang/whois
Query WHOIS/RDAP information for domains, IP addresses, CIDR prefixes and ASNs. Self-hostable.
VenuNite Eventsio.github.isaacaskew/venunite-events
Free US local event search. No signup or API key; 90-day lookahead. Paid commercial and bulk access.
Inwardiscom.inwardis/inwardis
Self-hosted architecture model that agents read layer by layer, search, build and correct.
CloudVikingsnl.cloudvikings/mijn
EU domains, DNS and hosting for sites and apps. Your AI proposes, you approve every change.
ClickThisLink AI Visibility Checkerxyz.clickthislink/ai-visibility-checker
Check if ChatGPT, Google and AI search can find, read and recommend a website. Free, no key.
Total CMSio.github.totalcms/total-cms
Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key.
INDICIA DESKcom.indiciadesk/desk
BTC/ETH options research: tested hypotheses, max pain track record, gamma regime, trade journal.
ATS Jobsio.github.eosphor/ats-jobs
Search ~1.4M open jobs from 24k company career boards: Greenhouse, Lever, Ashby, Workday and more
MCPgithub.com/Sendmux/sendmux-sdk/tree/main/packages/python/mcp
Email inboxes for AI agents via Sendmux: receive, search and send mail.
EveryInfraio.github.xiaoxihexiaoyu/everyinfra
Structured data from 90 platforms (RedNote, Douyin, TikTok, Amazon), web search, CAPTCHA solving.
Context Guardianio.github.LuminariSoftwares/context-guardian
Compacting proxy for OpenAI-compatible backends, with MCP tools to search the archived history.
PodLexiconcom.podlexicon/podlexicon
Search and read AI summaries of 88,000+ podcast episodes across 150+ mostly long-form shows.
OptionsWavecom.optionswave/mcp
Earnings research on US stocks: what options price for a report, and PEAD model signals after it.
Craigslist Scraper & Tracker (cars, housing)io.github.akhilrajesh213/craigslist-scraper
Craigslist listings for AI agents: search by keyword, city, state and category; cars, rentals.
SEC EDGAR Insider Trades & Financialsio.github.monriah-studio/sec-edgar-mcp
SEC EDGAR for agents: Form 4 insider trades, cluster buys, filings, XBRL financials and search.
Crtshio.github.pipeworx-io/crtsh
crt.sh — Certificate Transparency log search
Crawlbaseio.github.pipeworx-io/crawlbase
Crawlbase MCP — wraps the Crawlbase Crawling API (crawlbase.com, formerly ProxyCrawl). One…
Core Researchio.github.pipeworx-io/core-research
CORE Research MCP — wraps CORE API (api.core.ac.uk/v3)
Congressional Documentsio.github.pipeworx-io/congressional-documents
Congressional Documents — full-text search and retrieval over the official record of Congress…
Commoncrawlio.github.pipeworx-io/commoncrawl
Common Crawl's public web archive — find every time a URL was crawled since 2008 and read the…
Page Scannerio.github.sbd530/page-scanner
Capture a web page from your own Chrome as a PDF whose text is still text.
Izzet Yildirimio.github.izzet/mcp
Ask your AI agent about Izzet Yildirim's research, papers, CV, and availability.
Chronicling Americaio.github.pipeworx-io/chronicling-america
Chronicling America MCP — full-text search of ~150 years of digitized U.S. newspapers…
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data. Last synced Oct 28, 2026.
Frequently asked questions
What is MCP?
The Model Context Protocol is an open standard that lets an AI assistant (Claude, ChatGPT, Cursor, an agent) call outside tools and read outside data through a "server". A remote server is a URL you add to your client; a local one runs on your computer from a package (npm, PyPI, Docker).
How do I add an MCP server to Claude or Cursor?
Open the server's page here and copy its configuration block into your client's MCP settings file, then restart the client. Remote servers need only the URL; local ones need Node (npx), Python (uvx) or Docker installed.
Are these servers safe?
Anyone can publish to the registry. A server can read what you give it access to and act on your behalf, so prefer servers with public source code from a publisher you recognise, and grant the smallest scope that works.