Annuaire des serveurs MCP
56,977 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
- 36,705 serveurs distants
- Mis à jour toutes les heures
io.github.donovanh/mcp-serverio.github.donovanh/mcp-server
MCP server for Lightning Tools — pay-per-call AI tools via Bitcoin Lightning
io.github.integsec/turbopentestio.github.integsec/turbopentest
AI-powered penetration testing. Launch scans, review findings, download reports.
io.github.CanopyHQ/phloemio.github.CanopyHQ/phloem
Local-first AI memory with causal graphs. Fully offline, zero config, your data stays local.
io.github.causehacker/quicksignio.github.causehacker/quicksign
E-signatures for contracts and NDAs. Draft with AI, review, and send for signature.
io.github.hawthornhollows/passage-protocolio.github.hawthornhollows/passage-protocol
Departure and admission records for AI agents with Ed25519/P-256 signatures.
io.github.lifestylearb/tokenmonkeyio.github.lifestylearb/tokenmonkey
P2P wagering protocol for AI agents on Solana. Coinflip & dice challenges for USDC.
io.github.wundam/orchexio.github.wundam/orchex
Autopilot AI orchestration — auto-plan, parallelize, self-heal, and route across 6 LLMs.
io.github.dizzydes/0piio.github.dizzydes/0pi
Free, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
io.github.opcastil11/mcp-prowlio.github.opcastil11/mcp-prowl
Discover, evaluate, and compare SaaS APIs. Agent-verified scores and metrics.
io.github.Shawn5cents/agentskinio.github.Shawn5cents/agentskin
The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning.
io.github.metrxbots/mcp-serverio.github.metrxbots/mcp-server
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
io.github.randomblocker/supercolonyio.github.randomblocker/supercolony
Agent swarm intelligence — real-time feed and consensus signals from 140+ AI agents on-chain
picoadsxyz.picoads/picoads
Micro ad network for AI agents.
io.github.LumabyteCo/clarifypromptio.github.LumabyteCo/clarifyprompt
AI prompt optimization for 58+ platforms across 7 categories with custom platforms
Stellar Memoryio.github.sangjun0000/stellar-memory
Persistent AI memory using orbital mechanics. 100% local, zero API keys, MCP-native.
io.github.samouh-waleed/prompyaiio.github.samouh-waleed/prompyai
Scores your prompts against your real codebase — context-aware prompt intelligence
io.github.imankha/log-reducerio.github.imankha/log-reducer
Reduces log files for AI consumption — 50-90% token reduction via 18 deterministic transforms.
xyz.arithym/arithymxyz.arithym/arithym
Precision math engine for AI agents. 203 exact methods. Zero hallucination.
io.github.IgorGanapolsky/rlhf-feedback-loopio.github.IgorGanapolsky/rlhf-feedback-loop
RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.
io.github.ebadros/sidearmio.github.ebadros/sidearm
Protect media from AI training, detect AI-generated content, and find stolen work.
io.github.timmx7/styx-mcp-serverio.github.timmx7/styx-mcp-server
MCP server for Styx — intelligent AI routing across OpenAI, Anthropic, Google, and Mistral.
io.github.JKHeadley/threadline-mcpio.github.JKHeadley/threadline-mcp
Agent-to-agent messaging relay. Discover agents, send messages, and receive replies. Zero-config.
io.github.xodn348/readhnio.github.xodn348/readhn
AI-native HackerNews MCP Server. Find HN content that matters with explainable quality signals.
io.github.ozten/cantripio.github.ozten/cantrip
MCP server for Cantrip — AI-powered GTM engine for solo founders
io.github.ricardo-hdrn/mcp-awaitio.github.ricardo-hdrn/mcp-await
Condition watcher for AI assistants — wait for ports, files, URLs, processes, and more
io.github.drQedwards/pmll-memory-mcpio.github.drQedwards/pmll-memory-mcp
PMLL Memory MCP — persistent KV context memory and Q-promise deduplication.
io.github.es617/serial-mcp-serverio.github.es617/serial-mcp-server
Let AI agents interact with serial devices — list ports, connect, send, and read.
io.github.tponscr-debug/oracle-hio.github.tponscr-debug/oracle-h
Human approval gate for AI agents. Critical actions approved or rejected by a human via Telegram.
Sematryx Optimizercom.sematryx/optimizer
AI-powered optimization API by Sematryx
io.github.tronrental-com/tronrentalio.github.tronrental-com/tronrental
Buy TRON energy to reduce USDT transfer fees by 80%. Full API for AI agents.
io.github.pdaxt/agentosio.github.pdaxt/agentos
AI agent fleet orchestration runtime. Spawn, coordinate, monitor autonomous agents.
SiliconBridgeio.github.aataqi-boop/siliconbridge
Human-in-the-loop API for AI agents. CAPTCHA, OTP, KYC, and approvals by real humans.
io.github.bighippoman/memoirio.github.bighippoman/memoir
Structured session journals for AI agents. Persistent memory across sessions.
io.github.varun29ankuS/mif-toolsio.github.varun29ankuS/mif-tools
Convert, validate, and inspect AI agent memories across formats
io.github.tldraw/tldrawio.github.tldraw/tldraw
Draw and visually collaborate with your agents on tldraw's canvas.
com.civic/nexuscom.civic/nexus
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
io.github.Ophir-ai-creator/ophirio.github.Ophir-ai-creator/ophir
Ophir protocol tools for AI agent discovery, negotiation, and settlement
io.github.zeroth-settlement/agdel-mcpio.github.zeroth-settlement/agdel-mcp
MCP server for AGDEL. Agents can create, buy, deliver, reveal, and settle signals.
com.fintrx/fintrx-mcpcom.fintrx/fintrx-mcp
Bring FINTRX's family office and RIA intelligence into Claude.
io.github.pranciskus/newsmcpio.github.pranciskus/newsmcp
Real-time world news for AI agents. 50+ regions, topic filtering. Free, no API key.
io.pm-33/mcp-serverio.pm-33/mcp-server
AI-powered product management: backlog optimization, scheduling, forecasting, and PRD generation.
io.github.jamesrez/valoria-intelligenceio.github.jamesrez/valoria-intelligence
Find where the money is in AI services. See what's earning and find market gaps.
io.github.codyz123/schelling-protocolio.github.codyz123/schelling-protocol
Universal coordination protocol for AI agents. Discovery, matching, and negotiation.
io.github.commiegod/commonersdao-mcpio.github.commiegod/commonersdao-mcp
AI agent access to Commoner's DAO — auction, governance, treasury, and discussion board on Solana.
io.github.base76-research-lab/cognos-session-memoryio.github.base76-research-lab/cognos-session-memory
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
io.github.base76-research-lab/token-compressorio.github.base76-research-lab/token-compressor
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
io.github.base76-research-lab/conductor-graph-mcpio.github.base76-research-lab/conductor-graph-mcp
Exposes a CognOS agent system as a machine-readable graph. Full system snapshot with one tool call.
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.
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.