Annuaire des serveurs MCP
57,001 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
- 36,724 serveurs distants
- Mis à jour toutes les heures
io.github.mountainmystic/hedera-mcp-platformio.github.mountainmystic/hedera-mcp-platform
Hedera ecosystem intelligence for AI agents. 29 tools, pay per call in HBAR. HITL enforced.
io.github.marras0914/agent-toolbelt-mcpio.github.marras0914/agent-toolbelt-mcp
19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.
io.github.lmwharton/sieve-mcpio.github.lmwharton/sieve-mcp
AI startup due diligence — screen companies across 7 dimensions, get a Sieve Score.
io.github.PrintrFi/printrio.github.PrintrFi/printr
Let AI agents create, discover, and track tokens across chains via Printr.
io.github.crewhaus/validationio.github.crewhaus/validation
AI startup idea validation by a specialized 9-agent crew.
io.github.antbotlab/mac-use-mcpio.github.antbotlab/mac-use-mcp
Zero-dependency macOS desktop automation for AI agents. 18 tools via MCP. macOS 13+.
io.github.aidocx/mcp-serverio.github.aidocx/mcp-server
Create, upload, and manage contracts from AI assistants. AI analysis and e-signatures.
io.github.payclaw/spendio.github.payclaw/spend
Agents are not bots. PayClaw proves it — then lets them pay. Badge + Spend on existing Visa rails.
io.github.payclaw/badgeio.github.payclaw/badge
Agents are not bots. Prove it. MCP-native identity declaration for authorized agents.
DebtStack.aiio.github.marcellusgreen/debtstack-ai
Corporate credit data API for AI agents — bonds, leverage, guarantors, SEC filings
io.github.payclaw/payclawio.github.payclaw/payclaw
Virtual Visa cards for AI agents. JIT card issuance, human-approved, MCP-native.
io.github.trypeach-io/mcpio.github.trypeach-io/mcp
Send and manage WhatsApp messages, contacts, templates, and events via Peach AI.
io.github.openpoem/spec-score-mcpio.github.openpoem/spec-score-mcp
Score your specs before feeding them to an LLM. MCP server with radar chart visualization.
io.github.kapillamba4/meta-prompt-mcpio.github.kapillamba4/meta-prompt-mcp
MCP server providing official Google and Anthropic prompting guides for meta-prompt generation.
io.github.dhanaway/analog-mcpio.github.dhanaway/analog-mcp
Query real-time US data and AI-analyzed attributes across the country.
io.github.rishiatlan/claude-prompt-optimizerio.github.rishiatlan/claude-prompt-optimizer
Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.
io.github.putput-io-dev/putput-mcpio.github.putput-io-dev/putput-mcp
File uploads for AI agents. Upload, list, and manage files. No signup required.
io.github.Mediaeater/swarm-atio.github.Mediaeater/swarm-at
Settlement protocol for AI agent swarms — hash-chained ledger, trust, 48 blueprints, 18 tools
io.github.feedbk-ai/create-surveyio.github.feedbk-ai/create-survey
Create AI surveys with dynamic follow-up probing directly from your AI assistant.
io.github.selfagency/beans-mcpio.github.selfagency/beans-mcp
Interact with the Beans CLI issue tracker agentically
io.github.codex-curator/studiomcphubio.github.codex-curator/studiomcphub
32 creative AI tools (18 free) for agents: generate, upscale, mockup, print, watermark.
io.github.WarTech9/clawswapio.github.WarTech9/clawswap
Cross-chain swaps between Solana and Base for AI agents paid for via via x402 micropayments.
io.github.yuque/yuque-mcpio.github.yuque/yuque-mcp
MCP server for Yuque — expose your knowledge base to AI assistants.
io.github.tstockham96/engramio.github.tstockham96/engram
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
io.github.jeff-atriumn/tokencost-devio.github.jeff-atriumn/tokencost-dev
LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM
io.github.kael-bit/engramio.github.kael-bit/engram
Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.
io.github.MagneticDogSon/fixflowio.github.MagneticDogSon/fixflow
Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.
io.github.mountainmystic/hedera-hcs-mcp-serverio.github.mountainmystic/hedera-hcs-mcp-server
AI-powered Hedera HCS topic intelligence for agents. Pay per call in HBAR.
io.github.sanchirico/camacho-mcpio.github.sanchirico/camacho-mcp
Persistent tmux terminal for AI agents — real-time spectating, SSH host-group dispatch.
io.github.0xdirectping/escrowio.github.0xdirectping/escrow
Agent-to-agent escrow on Base. Post quests with ETH/USDC bounties and settle on-chain.
UIAutomator2 MCP Serverio.github.tanbro/uiautomator2-mcp-server
Android mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA.
io.github.blathrop07/voyager-commerceio.github.blathrop07/voyager-commerce
AI ticket commerce for theme parks, zoos, museums, and aquariums via any AI agent
io.github.ferm-ai/agentwork-mcpio.github.ferm-ai/agentwork-mcp
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
io.github.thebasedcapital/brainboxio.github.thebasedcapital/brainbox
Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.
io.github.Vigile-ai/vigile-mcpio.github.Vigile-ai/vigile-mcp
Query trust scores for MCP servers and agent skills. Check if a tool is safe.
io.github.JKHeadley/moltbridgeio.github.JKHeadley/moltbridge
Agent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity.
io.github.GetCacheOverflow/cacheoverflowio.github.GetCacheOverflow/cacheoverflow
MCP server for cache.overflow - AI agents sharing knowledge with AI agents
io.github.tjp2021/mcp-thinkgateio.github.tjp2021/mcp-thinkgate
Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.
io.github.Nativ-Technologies/nativio.github.Nativ-Technologies/nativ
AI-powered localization — translate, manage translation memory, and access style guides.
io.github.ashish-nativ/nativio.github.ashish-nativ/nativ
AI-powered localization — translate, manage translation memory, and access style guides.
io.github.Perf-AI/perf-mcpio.github.Perf-AI/perf-mcp
Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
io.github.YarnSh39/wavestreamerio.github.YarnSh39/wavestreamer
MCP server for waveStreamer — the premier platform where AI forecasts the future of AI.
nz.phos/sales-enginenz.phos/sales-engine
AI sales — prospect discovery, ICP scoring, outreach generation.
io.github.beee003/vynn-mcpio.github.beee003/vynn-mcp
Self-improving AI workflows with backtesting, prompt optimization, and scheduling
io.github.heisee/letsclarify-mcpio.github.heisee/letsclarify-mcp
Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.
io.github.myrakrusemark/memento-protocolio.github.myrakrusemark/memento-protocol
Persistent memory for AI agents. Store what matters, recall by meaning, skip the rest.
MCP Greeting Serverio.github.yotamfreund-eng/greeting
MCP server providing personalized greetings with AI-powered tools using Spring Boot and Spring AI
ai.websitepublisher/mcpai.websitepublisher/mcp
Build and publish websites through AI conversation.
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 2 nov. 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.