Annuaire des serveurs MCP
54,683 serveurs MCP qui relient les assistants IA à des outils et des données, issus du registre MCP officiel et des listes communautaires, mis à jour toutes les heures.
- 16 catégories
- 34,875 serveurs distants
- Mis à jour toutes les heures
Israeli supermarket prices (Foodiepedia)il.co.foodiepedia/prices
Prices in 31 Israeli supermarket chains by barcode. Free search; API key or x402 pay-per-call.
Cerulean Jobscom.ceruleanjobs/search
Open jobs at luxury houses and brands worldwide: search them, read one in full, find roles like it.
LIGHTS OUT WORKS Capability Searchio.github.LightsOutWorks/agent-commons
Evidence-labeled Method search for AI Agents; optional contributor and Gateway discovery.
Oxylabsio.github.pipeworx-io/oxylabs
Oxylabs MCP — Oxylabs Web Scraper API (oxylabs.io)
SnoopScancom.snoopscan/snoopscan
Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.
Reverieai.knowall/reverie
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
ProjectThundercom.projectthunder/site
ERP and B2B ecommerce rollout research: ERP fit, migration plans, site scans, ERP partner directory.
Serato DJ libraryio.github.Venut-Technologies/serato-dj-mcp
Ask AI about your Serato library: harmonic search, crate audits, previewed crate building.
Odiseohelp.odiseo/mcp
SEO layer for agents: research, content, QA, approvals and publishing via MCP OAuth.
LINE WORKS AiNote (unofficial)io.github.iwaohig/lineworks-ainote-mcp
Unofficial read-only access to LINE WORKS AiNote meeting notes: list, search, summaries, transcripts
Dinogamegg.dinogame/games
Search 101 free browser games + 1,000 Chrome Dino & gaming guides; returns dinogame.gg play links.
Anthony Hunt · SHAART Agency docscom.anthonyhunts/shaart-agency-docs
Search anthonyhunts.com and read any page as Markdown: GoHighLevel and AI automation guides
OxaDashfr.oxadash/oxadash
Gérez vos sites, serveurs de jeu, VPS, DNS et mails OxalisHeberg.
Evercraft Webio.github.jgaethle10/evercraft-web
Read public web content with Evercraft; search and browser automation stay behind safety gates.
Bandcamp crate diggingio.github.Venut-Technologies/bandcamp-mcp
Dig Bandcamp from any AI assistant: search artists, albums, labels and tracks, browse genre tags.
GoAI Moat Web Scrapecom.goaimoat/web-scrape
Scrape any URL into clean LLM-ready Markdown, or crawl a whole site.
GoAI Moat Company Intelcom.goaimoat/company-intel
Company profile lookup and B2B company search for AI agents.
Public Browserio.github.Silbercue/public-browser
Chrome over CDP for AI agents. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -32% time
GoAI Moat Google Searchcom.goaimoat/google-search
Google web and news search for AI agents.
Signed Investorscom.signed/investors
Search Signed's public angel investor directory by sector, check size, or keyword. No login needed.
Fec MCP Servergithub.com/sh-patterson/fec-mcp-server
Query FEC campaign finance data via the OpenFEC API: search candidates, track donations, analyze spending and monitor Super PAC activity.
Legiscan MCPgithub.com/sh-patterson/legiscan-mcp
Legislative data from all 50 US states and Congress via the LegiScan API: search bills, get full text, track votes and look up legislators.
Evercraft Deck Capital Fitio.github.jgaethle10/deck-capital-fit
Capital-fit research and founder readiness with human-confirmed checkout.
Seayoracom.seayora/seayora
Property management and rental search: portfolio, rent, leases, repairs and listings.
AgentCDN ARVcom.agentcdn/arv
Agent-Ready Video (ARV): search video moments, moment context, rights, and signed playback
HireHeat Jobs: Career Site Job Listings from 12,000+ Companiesio.github.shawmena-dotcom/career-site-jobs
HireHeat Jobs: search jobs on 12,000+ company career sites (Greenhouse, Ashby, Workable…).
MCP Servergithub.com/discava/mcp-server
Search local businesses worldwide, with confidence scores and agent trust rankings.
SEO-IntentRank (Antigravity MCP)io.github.AI-BuildInfra/SEO-intentrank
Human search intent keywords, Core Web Vitals, technical SEO & on-page audit MCP server.
HasData YouTubecom.hasdata/youtube
Search YouTube and read video, channel and transcript data as JSON. No Google Cloud project.
HasData Yelpcom.hasdata/yelp
Yelp business search, place details and the full review feed, as structured JSON.
HasData Yellow Pagescom.hasdata/yellowpages
Yellow Pages local business search and full business listings, as structured JSON.
HasData Web Scrapingcom.hasdata/web-scraping
Fetch any public web page through managed proxies, with optional JS rendering and extraction rules.
HasData Walmartcom.hasdata/walmart
Walmart search, product pages and customer reviews on walmart.com and walmart.ca, as JSON.
HasData TikTokcom.hasdata/tiktok
Public TikTok profiles, videos, comments and keyword search as JSON. No developer account.
HasData Google Search (SERP)com.hasdata/google-search
Google SERP as JSON: organic, AI Overview, People Also Ask, AI Mode, news, shopping. No Cloud setup.
HasData Google Scholarcom.hasdata/google-scholar
Google Scholar search results, citation counts and citation export formats, as structured JSON.
HasData Google Hotelscom.hasdata/google-hotels
Google Hotels search: rates, ratings, amenities and what each booking site charges, as JSON.
HasData DuckDuckGocom.hasdata/duckduckgo
DuckDuckGo search as JSON. Ranked results, ads in their own array, 37 regions.
HasData Bingcom.hasdata/bing
Bing search results with the ad block and Copilot answer, geo and market targeting, as JSON.
HasData Amazoncom.hasdata/amazon
Amazon keyword search, product details, seller profiles and seller catalogues, as structured JSON.
Iminifycom.iminify/iminify
Compress, convert and resize images, and scan web pages for every image they load.
LiquiLens — the Failure Radario.github.beepboop2025/liquilens
Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key.
Handsontable Docs MCP Servercom.handsontable/docs
Semantic search over Handsontable and HyperFormula docs, API reference, release notes, and issues.
GetYourJobpro.getyourjob/getyourjob
French IT job search, AI candidate-offer matching, application tracking and cover letters.
VibeSEOdev.vibeseo/vibeseo
SEO research, keyword discovery, site audits, Search Console, backlinks and content workflow.
Recapp — Loom for agentsdev.recapp/recapp
Loom for agents: AI agents record narrated product demos, plus transcripts, summaries, and search.
mcpnav directorydev.mcpnav/directory
Search a directory of MCP servers and get connect configs. Data is CC0/MIT-licensed.
DomainDNA: Tech Stack Detector, WHOIS & Domain Age APIio.github.shawmena-dotcom/domain-intel
DomainDNA: a domain's tech stack, email security (MX/SPF/DMARC), TLS expiry and age in one record.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données. Dernière synchronisation 30 oct. 2026.
Questions fréquentes
Qu’est-ce que MCP ?
Le Model Context Protocol est un standard ouvert qui permet à un assistant IA (Claude, ChatGPT, Cursor, un agent) d'appeler des outils et de lire des données externes via un « serveur ». Un serveur distant est une URL à ajouter à votre client ; un serveur local tourne sur votre ordinateur à partir d'un paquet (npm, PyPI, Docker).
Comment ajouter un serveur MCP à Claude ou Cursor ?
Ouvrez la page du serveur ici, copiez son bloc de configuration dans le fichier de réglages MCP de votre client, puis redémarrez-le. Un serveur distant n'a besoin que de l'URL ; un serveur local demande Node (npx), Python (uvx) ou Docker.
Ces serveurs sont-ils sûrs ?
N'importe qui peut publier dans le registre. Un serveur peut lire ce à quoi vous lui donnez accès et agir en votre nom : préférez ceux dont le code est public et l'éditeur reconnu, et accordez le minimum de droits.