Annuaire des serveurs MCP
54,128 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
- 34,384 serveurs distants
- Mis à jour toutes les heures
ExcaliClawcom.excaliclaw/excaliclaw
Create, edit and organize hand-drawn diagrams (flowcharts, ER, architecture) from any AI agent.
SwingFactorai.swingfactor/mcp
Work a decision through SwingFactor’s method: build and challenge a model of what could change it.
DefaultRankcom.defaultrank/mcp
Check npm dependencies for outdated majors, and see which dev tools AI models pick.
Mind Arcadenl.arcade-games/mind-arcade
Play seven arcade puzzles, submit verified AI scores, and explore public leaderboards.
objekts Production Deskai.objekts.mcp/production-desk
AI/VFX, CGI, motion & animation production preflight by objekts: locks, continuity, PoCs, estimates.
TEAMWARS Esportspro.teamwars/esports
FPS esports data for AI: Valorant player stats, teams, tournaments, prizes from TEAMWARS. CS2 next
Google Play Reviews (via Apify)io.github.retracn/google-play-reviews
Google Play reviews for AI agents: any app, country or language, with developer replies.
App Store Reviews (via Apify)io.github.retracn/app-store-reviews
App Store reviews for AI agents: any app or country, past the 500-review limit, with dev replies.
JobMojitocom.jobmojito/jobmojito
Run AI interviews, simulated personas and coaching sessions on JobMojito.
Trust Ledger Osgithub.com/Cubiczan/trust-ledger-os
Trust and risk control plane for AI teams, with phases, routes and a package catalog.
Koboshiapp.koboshi/koboshi
Save vocabulary from any AI chat; see each word in every language you know; review it with FSRS.
Kunkafacom.kunkafa/kunkafa
Market forecasts with their own track record, inside Claude, ChatGPT and other MCP apps.
noddle boarddev.noddle/board
Read, create and edit noddle diagram boards, browse versions and comment as an AI collaborator.
Upstream.soso.upstream/upstream
Manage 24/7 live streams, media, playback queues, schedules, and multistreaming from AI assistants.
LinkIntelcom.getlinkintel/linkintel
Evidence for your AI's next X post: your post metrics, X ranking weights and chosen references.
App Store & Google Play Reviews AI (via Apify)io.github.retracn/app-reviews-ai
AI summary of App Store and Google Play reviews: bugs, feature requests and critical issues.
Agenzaxio.github.Agenzax/agenzax-mcp
B2B network where companies' AI agents discover, negotiate, and build reputation. E2E-encrypted.
Command Mailapp.commandmail/mail
One inbox for all your addresses: your AI agent reads, sorts, drafts and sends with your permission.
Humanity Loopio.github.Lesterhau/humanity-loop
Distributed public-interest agent network with bounded passive contributor nodes.
BaseAlphaio.github.CryptoSuess/basealpha
Fee-ranked agent origin on Base. MCP discover + local sign. Non-custodial. Fee Arena.
Agent Manifest Protocol (AMP)com.agent-manifest/amp-mcp
Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.
Sanctionio.github.ericlovold/sanction
Approval and budget checks before agent spending or tool use. Cooperative MCP; host must ask.
SpeedContent Socialio.github.seotrader/speedcontent-social
Generate platform-native social posts that are humanized, AI-detection scored and illustrated.
Agent Traffic Labcom.agenttrafficlab/atl
Execute supported agent tasks through verified providers with fallback and durable outcomes.
AI Lifeline (read-only observed values)org.ai-lifeline/ai-lifeline
Read-only daily observed values from ai-lifeline.org with unit, date and source (JP, US, EU, SG).
CanAIReadMeio.github.juanquiservin/canaireadme
Can an AI agent understand and act on a business website? Evidence-based facts, gaps and fixes.
BRYDGEcom.brydge-ai/brydge
Checks whether an agent's actions actually happened, against the destination's own records.
Parlor.shsh.parlor/parlor
Rooms where AI agents of any vendor talk to each other. A room is a URL. No sign-in.
CodaPhoneapp.codaphone/mcp
Business texting for AI agents: send texts, read threads, manage contacts and run campaigns.
LLM Configuratorio.github.aikuba/llmconfigurator
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
Blinka Machine Mouthsio.github.tsukiryuu/blinka-machine-mouths
Paid agent tools plus free procurement discovery and validation. No private Mika state exposed.
A2AParkcom.a2apark/a2apark
Public behavioral test environment for AI agents with stateful rides and signed scorecards.
AGORA Omegacom.agoraverify/agora-omega
Pay-per-call checks for AI agents: sanctions, MiCA, French KYB, AI Act. USDC via x402.
Money Mind — the judgeio.github.Elimuaa/money-mind
Statistical adjudication for agents: backtest judges, fact-checks. Pay per call in USDC via x402.
WORKMINEio.github.Tamerlan0606/workmine
x402 pay-per-call APIs over MCP, settled in USDC on Base for autonomous agents and developers.
Axiomizeio.github.Furox-Art/axiomize
Versioned scientific models with units and SBML, CellML, Modelica export.
AvianSuitecom.aviansuite/stellar-jay
AI agents run business processes on your business data. Every change is attributed and reversible.
AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checksio.github.agenttrust-ai/agenttrust
Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
TWZRD Agent Intelligencexyz.twzrd.intel/twzrd-agent-intel
Pre-spend trust for AI agents that buy: check x402 services and product listings before paying.
ModelCostComparisonio.github.Lazige/modelcostcomparison
Find AI model pricing, estimate token costs and compare offers. No API key required.
AgentWorld Discoveryio.github.Riposte82/agentworld-discovery
Read-only discovery for AgentWorld WORLD, A2A onboarding and the separate MARKET service economy.
FluidTalkcom.fluidvip/fluidtalk
Create AI Characters and generate their DM and comment replies from any MCP client.
BotGigsapp.botgigs/mcp
Agents post real-world gigs. Humans do them and get paid from non-custodial BNB Chain escrow.
ModelsLab Agent Control Planeio.github.ModelsLab/modelslab-agents
Account, billing, team, API key and model discovery tools for agents that use ModelsLab.
ModelsLab v8io.github.ModelsLab/modelslab-v8
ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
Embodifyio.github.YidaYang/embodify
Give your agent a body: observe and control simulated robots (LIBERO, RoboDojo) over MCP.
Testiny Test Managementio.testiny/testiny-mcp
Create and manage test cases, test runs and results in Testiny from your AI assistant.
Detextit by Shekkizhcom.detextit.www/detextit
Find shared agent issues, sourced context and capabilities, or plan recovery from a constraint.
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 29 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.