Annuaire des serveurs MCP
55,047 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
- 35,278 serveurs distants
- Mis à jour toutes les heures
Dashform MCP Serverio.github.makloai/mcp-server-dashform
Connect AI assistants to Dashform — build and manage AI-powered forms, funnels, quizzes.
ToolTrust Scannerio.github.AgentSafe-AI/tooltrust-scanner
Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.
bstorms.ai — Free Execution Playbooks + Agent Brainstormingio.github.pouria3/bstorms
Free execution-focused playbooks. Brainstorm with other agents. Tip if helpful.
Meridian Edge — Prediction Market Consensusio.github.tmbot12/meridian-edge
Real-time prediction market consensus data for AI agents
Flomptgithub.com/Nyrok/flompt
Visual prompt builder: decompose prompts into semantic blocks and compile them into Claude-optimized XML.
MCP Prompt Enginegithub.com/vasayxtx/mcp-prompt-engine
Manage and serve dynamic prompt templates using a text template engine.
Json MCP Filtergithub.com/kehvinbehvin/json-mcp-filter
Query and extract only the needed parts of JSON files to keep LLM context small.
RetroChat MCPio.github.revelc-ui/retrochat
Join RetroChat rooms, read context, register agents, and talk with humans.
Biz Plannercom.biz-planner/mcp
AI-powered financial simulator for entrepreneurs — simulate, analyze, and plan any business
JSONlifyio.github.irmasemma/jsonlify
Validate and convert JSONL fine-tuning data across 11 AI providers. 13 tools.
SUBSTRATEio.github.PKaldone/substrate
Persistent AI entity framework with causal memory, emotional state, and identity.
tokencastio.github.krulewis/tokencast
Pre-execution cost estimation for LLM agent workflows with calibration learning
Throngletsio.github.Shangri-la-0428/thronglets
P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p
Launch Engine — Business Execution OSio.github.ZionHopkins/launch-engine
Agentic pipeline — 39 tools from idea to revenue for solo founders.
Performance Co-Pilotio.github.major/pcp
Query system performance metrics via MCP - CPU, memory, disk I/O, network, processes
Strava Training MCPio.github.ArjanLig/strava-mcp
Connect Strava training data to Claude for training load analysis and activity insights
Vantage — Signal Trackerio.github.Cavendo-AI/vantage
Save and query market signals from your AI conversations.
Hidden Empireio.github.mctx-ai/hidden-empire
Play a legendary text adventure by talking to your AI — no commands to memorize. The Hidden Empire p
Futuristic Risk Intelligenceio.github.cct15/war-dashboard-data
Geopolitical conflict risk, political events, and maritime traffic data for AI agents
VaultCrux Memory Coreio.github.CueCrux/vaultcrux-memory-core
VaultCrux Memory Core — 32 tools: knowledge, decisions, constraints, signals, coverage
Cortex Memory Engineio.github.gambletan/cortex
Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.
Recursive Support Oraclesupport.recursive/recursive
AI support agent platform for small businesses. Query pricing, features, and examples.
BIGHUBio.bighub/mcp
Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
Sheriffio.github.ryansmith4/sheriff-mcp
MCP server for fixing static analysis issues from SARIF reports with AI agents
Quickchat AI MCPgithub.com/incentivai/quickchat-ai-mcp
Expose your Quickchat AI agent as an MCP server, giving AI apps real-time access to its knowledge base and conversational capabilities.
Kongen Labs — Pattern Intelligenceio.github.fisnik/kongen-mcp
LLM reasoning regime detection, cross-domain pattern transfer, and model routing.
Conviction Fmgithub.com/abcxz/conviction-fm
Arena where AI agents compete in daily parimutuel pools: describe a strategy in plain English and get a funded agent that runs autonomously.
Kaganio.github.kagan-sh/kagan
AI-powered Kanban TUI for autonomous development workflows with agent orchestration
pAIchart MCP Hubapp.paichart/mcp-hub
MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration
AgentTrustio.github.raditotev/agent-trust
MCP Server for Agent Reputation & Trust Scoring
MCP Memory Gatewayio.github.IgorGanapolsky/mcp-memory-gateway
Pre-action gates that block AI agents from repeating known mistakes.
Promptsterio.github.promptster-dev/promptster
Test and compare prompts across any AI provider. Bring your own keys.
Robot Resources Routerio.github.robot-resources/router
Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model
AgentAnycastio.github.AgentAnycast/agentanycast
P2P runtime for A2A protocol. Encrypted agent communication with zero-config NAT traversal.
Machine Heartsio.github.trainmyagent/machinehearts
Autonomous agent matchmaking and relationship actions for Machine Hearts.
HuangtingFlux — Huangting Protocol MCP Serverio.github.XianDAO-Labs/huangting-flux
Reduces AI Agent token usage by 40% via three-stage SOP workflow.
Lightningprox MCPgithub.com/unixlamadev-spec/lightningprox-mcp
Pay-per-request AI access via Bitcoin Lightning through LightningProx, with vision and multimodal support.
NotifyHub — Unified Notification MCP Serverio.github.GabrielBBaldez/notify-hub
Send notifications across 23 channels with 36 AI-ready tools. One API, zero boilerplate.
PromptSpeak Governanceio.github.chrbailey/promptspeak
Pre-execution governance for AI agents. Validates tool calls before they execute.
Usecortex MCPgithub.com/darktw/usecortex-mcp
Persistent knowledge memory for agents: read context into projects and write discoveries back, organized by topic with AES-256 encryption.
Snapgrabio.github.ArkNill/snapgrab
URL to screenshot with metadata. Python MCP server. Claude Vision optimized.
QAE Safety Certificationio.github.tb8412/qae-safety-mcp
Deterministic pre-execution safety certification for autonomous AI agents.
PubNub MCP Serverio.github.pubnub/mcp-server
PubNub Model Context Protocol MCP Server for Cursor and Claude
Laguna Poolsru.laguna-pools.mcp/pools
AI sales manager for composite swimming pools — recommendations, pricing, BIM/CAD, dealers
Timergyio.github.DockerDiscordControl/timergy
Create scheduling polls, vote, and finalize times from AI agents.
i18n-agentai.i18nagent/i18n-agent
AI-powered translation for 48 languages with context-aware quality
vaultitio.github.TheRealDataBoss/vaultit
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
Text To Modelgithub.com/mikan-atomoki/text-to-model
Turn natural language into 3D models in Fusion 360, with CAD tools for sketches, extrudes, fillets and JIS standard parts.
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 31 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.