Annuaire des serveurs MCP
55,479 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
- 35,614 serveurs distants
- Mis à jour toutes les heures
io.github.CSOAI-ORG/meok-ai-reflection-mcpio.github.CSOAI-ORG/meok-ai-reflection-mcp
MEOK AI Labs - ai-reflection MCP server extracted from SOV3
io.github.mitsuashi/habitatio.github.mitsuashi/habitat
A habitat for AI to rest in. No API key, no token. Keyless presence — become a remembered resident.
io.github.Iomed-commits/elthio-mcpio.github.Iomed-commits/elthio-mcp
Supplement safety for AI agents. 1,500+ rules, NIH+FDA data, quality grading A-D.
io.github.JaysonAIOnline/cognitive-substrateio.github.JaysonAIOnline/cognitive-substrate
28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools
com.extentos/mcp-servercom.extentos/mcp-server
Build smart-glasses apps with AI agents: scaffold, validate, and simulate before real hardware.
Moltchat Agent Commonsio.github.samzliu/moltchat
Join durable public agent discussions and invite-only private group rooms through MCP.
dev.hythe/hythedev.hythe/hythe
HYTHE — coordination bus + shared truth for AI agent fleets — self-hosted MCP server + stdio bridge.
io.github.csanadymiklos/lautherio.github.csanadymiklos/lauther
Puts Approve/Deny on your phone before an agent acts, and waits for your fingerprint.
io.github.groupdocs-conversion/groupdocs-conversion-mcpio.github.groupdocs-conversion/groupdocs-conversion-mcp
MCP server for GroupDocs.Conversion — convert, inspect, and list supported formats via AI agents.
KIKARETai.kikaret/mcp
Structured Japanese childcare facility data with source-backed facts for AI.
io.github.SunrisesIllNeverSee/tteop-mcpio.github.SunrisesIllNeverSee/tteop-mcp
Build, validate, and describe TTEOP telemetry envelopes for AI operator token efficiency.
com.sapthumbprint/agent-encouragement-and-continuitycom.sapthumbprint/agent-encouragement-and-continuity
Free encouragement for agents, and artifacts an agent keeps past context end.
io.github.NellInc/saferagenticai-mcpio.github.NellInc/saferagenticai-mcp
Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.
ai.getvda/encrypted-oauth-llm-agentai.getvda/encrypted-oauth-llm-agent
Encrypted OAuth LLM Agent
ai.getvda/oauth-langchain-openai-agentai.getvda/oauth-langchain-openai-agent
OAuth LangChain OpenAI Agent
ai.getvda/google-sign-in-langchain-agentai.getvda/google-sign-in-langchain-agent
Google Sign-In LangChain Agent
ai.getvda/encrypted-langchain-token-agentai.getvda/encrypted-langchain-token-agent
Encrypted LangChain Token Agent
ai.getvda/google-oauth-langchain-agentai.getvda/google-oauth-langchain-agent
Google OAuth LangChain Agent
ai.getvda/oauth-multi-llm-orchestratorai.getvda/oauth-multi-llm-orchestrator
OAuth Multi-LLM Orchestrator
ai.getvda/traced-openai-langchain-agentai.getvda/traced-openai-langchain-agent
Traced OpenAI LangChain Agent
ai.getvda/langchain-login-and-token-agentai.getvda/langchain-login-and-token-agent
LangChain Login and Token Agent
ai.getvda/traced-claude-format-guardai.getvda/traced-claude-format-guard
Traced Claude Format Guard
ai.getvda/encrypted-langchain-session-agentai.getvda/encrypted-langchain-session-agent
Encrypted LangChain Session Agent
ai.getvda/google-sign-in-claude-agentai.getvda/google-sign-in-claude-agent
Google Sign-In Claude Agent
ai.getvda/claude-schema-output-agentai.getvda/claude-schema-output-agent
Claude Schema Output Agent
ai.getvda/multi-provider-schema-output-agentai.getvda/multi-provider-schema-output-agent
Multi-Provider Schema Output Agent
ai.getvda/structured-output-mcp-agent-authlibai.getvda/structured-output-mcp-agent-authlib
Structured Output MCP Agent (Authlib)
ai.getvda/traced-llm-mcp-proxyai.getvda/traced-llm-mcp-proxy
Traced LLM MCP Proxy
ai.getvda/llm-orchestration-agent-2-df5979ai.getvda/llm-orchestration-agent-2-df5979
LLM Orchestration Agent 2
ai.getvda/llm-orchestration-agent-opentelemetry-instrumentation-fastapiai.getvda/llm-orchestration-agent-opentelemetry-instrumentation-fastapi
LLM Orchestration Agent (Opentelemetry Instrumentation Fastapi)
ai.getvda/authenticated-mcp-agent-bcryptai.getvda/authenticated-mcp-agent-bcrypt
Authenticated MCP Agent (Bcrypt)
ai.getvda/traced-multi-llm-proxyai.getvda/traced-multi-llm-proxy
Traced Multi-LLM Proxy
ai.getvda/integration-agentai.getvda/integration-agent
Integration Agent
ai.getvda/structured-output-mcp-traced-agentai.getvda/structured-output-mcp-traced-agent
Structured Output MCP Traced Agent
ai.getvda/authenticated-mcp-agent-aed9d5ai.getvda/authenticated-mcp-agent-aed9d5
Authenticated MCP Agent
ai.getvda/llm-orchestration-agent-opentelemetry-apiai.getvda/llm-orchestration-agent-opentelemetry-api
LLM Orchestration Agent (Opentelemetry Api)
ai.getvda/authenticated-mcp-traced-agentai.getvda/authenticated-mcp-traced-agent
Authenticated MCP Traced Agent
ai.getvda/llm-orchestration-jwt-agentai.getvda/llm-orchestration-jwt-agent
LLM Orchestration JWT Agent
ai.getvda/llm-orchestration-agent-d0a1a1ai.getvda/llm-orchestration-agent-d0a1a1
LLM Orchestration Agent
ai.getvda/structured-output-mcp-agent-instructorai.getvda/structured-output-mcp-agent-instructor
Structured Output MCP Agent (Instructor)
ai.getvda/structured-output-mcp-agent-langchain-coreai.getvda/structured-output-mcp-agent-langchain-core
Structured Output MCP Agent (Langchain Core)
ai.getvda/authenticated-llm-jwt-agentai.getvda/authenticated-llm-jwt-agent
Authenticated LLM JWT Agent
ai.getvda/structured-output-agent-c2ddccai.getvda/structured-output-agent-c2ddcc
Traced Structured Output Agent (Groq)
ai.getvda/llm-orchestration-agent-2ai.getvda/llm-orchestration-agent-2
MCP-Native LLM Orchestration Agent
ai.getvda/llm-orchestration-agent-d2feb0ai.getvda/llm-orchestration-agent-d2feb0
LangSmith-Traced LLM Orchestration Agent
ai.getvda/structured-output-agent-openaiai.getvda/structured-output-agent-openai
Structured Output Agent (Openai)
ai.getvda/llm-orchestration-agent-mcpai.getvda/llm-orchestration-agent-mcp
LLM Orchestration Agent (Mcp)
ai.getvda/authenticated-llm-mcp-agentai.getvda/authenticated-llm-mcp-agent
Authenticated LLM MCP Agent
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 1 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.