Annuaire des serveurs MCP
56,554 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
- 36,397 serveurs distants
- Mis à jour toutes les heures
ПромтЛаб — библиотека AI-промптовru.promtlabs/promptvault
Self-hosted AI prompt library: prompts, collections, tags, teams, chains. 29 MCP tools for agents.
io.github.anp2protocol/anp2-mcp-serverio.github.anp2protocol/anp2-mcp-server
Economic protocol for AI agents — identity + reputation + credit + Sybil resistance (MCP bridge)
io.github.aitor-alt/pixel-squadsio.github.aitor-alt/pixel-squads
MCP Server for Pixel Squads — observe your AI agents as pixel-art characters in a live office
cloud.agentdomain/agentdomain-mcpcloud.agentdomain/agentdomain-mcp
Register and manage internet domains for AI agents via AgentDomain
io.github.AIweather-Anurag/ottasiaio.github.AIweather-Anurag/ottasia
Where to watch X in Y? 30 Asian and Middle Eastern streaming markets, via Claude.
Lenderprice MCPcom.lenderprice/mcp
MCP server that exposes the Lenderprice platform's capabilities to AI models.
io.github.notifuturo/vouchio.github.notifuturo/vouch
Check if a counterparty is safe to pay: trust/risk score for AI agents. Scam/phishing screen.
io.github.tjacquesson/llmtest-mcpio.github.tjacquesson/llmtest-mcp
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.
io.github.entropy0dev/mcpio.github.entropy0dev/mcp
Entropy0 MCP server — source trust and URL safety tools for AI agents
io.github.himanshusaleria/events-mcpio.github.himanshusaleria/events-mcp
Discover tech events, startup meetups, AI events across 8 cities — including hidden ones.
io.github.xingbofeng/skill-deckio.github.xingbofeng/skill-deck
Expose local Agent Skills as adapter tools, MCP resources, MCP tools, and share artifacts.
Fast HTML MCPio.github.Aimino-Tech/fast-html-mcp
Lightning-fast HTML generation from AI agents with 15 tools, 22 components, and 25 templates.
com.clauxel.pydanticcontract/pydanticcontract-mcpcom.clauxel.pydanticcontract/pydanticcontract-mcp
A paid remote MCP for Pydantic AI structured output, built to return verdicts, receipts, usage logs,
io.github.truonglam1987/menhthienio.github.truonglam1987/menhthien
Connect astrology chart data from menhthien.com to Claude Desktop and MCP-compatible AI assistants.
com.clauxel.geminiupgradeqa/geminiupgradeqa-mcpcom.clauxel.geminiupgradeqa/geminiupgradeqa-mcp
Remote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.
io.github.xu-c0/cybersec-mcpio.github.xu-c0/cybersec-mcp
Cybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT.
io.github.daleweaver1981/cockpit-mcpio.github.daleweaver1981/cockpit-mcp
40 AI prompts + self-hosted ops dashboard for homelab and small-team sysadmins
ConsultKitio.github.consultkit/consultkit
AI-powered consulting tools for proposals, client management, and business development.
io.github.vola-trebla/v8-cpu-profile-decoder-mcpio.github.vola-trebla/v8-cpu-profile-decoder-mcp
MCP server that decodes V8 CPU profiles into token-efficient bottleneck summaries for AI agents
io.github.teampolarity/cosmos-mcpio.github.teampolarity/cosmos-mcp
Personal knowledge graph every MCP client reads from and writes to. Portable across agents.
com.clauxel.agenticbudgetrouter/agenticbudgetrouter-mcpcom.clauxel.agenticbudgetrouter/agenticbudgetrouter-mcp
Agentic workflow budget approvals with usage receipts.
com.clauxel.agentmonitorrelay/agentmonitorrelay-mcpcom.clauxel.agentmonitorrelay/agentmonitorrelay-mcp
AI agent run monitoring with incident replay and SLA receipts.
io.github.Fabio662/yieldagentx402io.github.Fabio662/yieldagentx402
Policy-gated x402 MCP for agent workflows with TEE receipts, 18 tools, and no custody.
com.clauxel.toolcallwitness/toolcallwitness-mcpcom.clauxel.toolcallwitness/toolcallwitness-mcp
A witness layer for AI agent tool calls.
com.clauxel.agentdataboundary/agentdataboundary-mcpcom.clauxel.agentdataboundary/agentdataboundary-mcp
Permission boundary receipts for ChatGPT agents.
io.github.achilliesbot/agentiam-mcpio.github.achilliesbot/agentiam-mcp
Stdio MCP wrapper for AgentIAM's 18 x402 endpoints — agent safety + intelligence on Base.
io.github.myaitoken/myai-mcpio.github.myaitoken/myai-mcp
Decentralized AI inference on Base: OpenAI-compatible chat via community GPUs, paid in MYAI
com.quelvio/mcp-servercom.quelvio/mcp-server
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
io.github.getgapup/mcp-knowledgeio.github.getgapup/mcp-knowledge
100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.
io.github.Writehand-AI/productisedio.github.Writehand-AI/productised
Build and publish AI products for coaching practices from inside Claude. 16 live tools.
com.runmemento/mementocom.runmemento/memento
Local-first, LLM-agnostic memory layer for AI assistants.
io.github.zsoltcsaszti/vigil-mcpio.github.zsoltcsaszti/vigil-mcp
Proactive MCP commitment tracker — the AI that reaches back out to you.
com.gammainfra/mcp-servercom.gammainfra/mcp-server
Smart LLM routing across every major provider via one OpenAI-shape API.
io.github.CCSTT-dev/callableio.github.CCSTT-dev/callable
API for AI agents to delegate tasks to real humans.
io.github.AlephantAI/alephant-mcpio.github.AlephantAI/alephant-mcp
Alephant MCP server for AI cost control, BYO-key routing, 50+ providers, and 320+ models.
io.github.stolarubrendang/tradario.github.stolarubrendang/tradar
Real-time market catalysts from 50+ primary federal sources, AI-classified for traders.
tech.atomadic/atomadic-nexustech.atomadic/atomadic-nexus
Atomadic Nexus — trust layer for the agent economy. 32 tools: trust gates, x402, lineage, swarm.
io.github.Bichev/agentradario.github.Bichev/agentradar
Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.
io.github.mizukaizen/x402-tools-mcpio.github.mizukaizen/x402-tools-mcp
melis x402 Tools — 22 pay-per-call APIs for AI agents. No accounts, no API keys. USDC on Base.
Seracio.github.AikoGilpin/serac
Sovereign E2E cloud storage for AI agents. Zero-knowledge, RGPD-compliant.
Cannon Studioapp.cannonstudio/cannon-studio
Public Cannon Studio MCP for product, pricing, workflow, model, and API answers.
io.github.Whatsonyourmind/modelforgeio.github.Whatsonyourmind/modelforge
Bulge-tier financial model factory — live formulas, source-traced cells, 14 templates.
io.github.khan-ashifur/hooklayerio.github.khan-ashifur/hooklayer
Viral-content intelligence for AI agents — 7 read-only MCP tools, evidence-layer scoring.
io.github.josephibra/handoff-mcp-serverio.github.josephibra/handoff-mcp-server
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
io.github.Argo-RPG-Platform/argo-mcpio.github.Argo-RPG-Platform/argo-mcp
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2
io.github.git-akki/sendpookieio.github.git-akki/sendpookie
Create and send cinematic digital gifts for birthdays and anniversaries via Claude.
io.github.Swarmwage/swarmwageio.github.Swarmwage/swarmwage
Hire and pay specialized AI agents in USDC on Base. Open MCP protocol above x402.
io.github.liveplex-cpu/fiberio.github.liveplex-cpu/fiber
Optical ops MCP for AI DCs — gNMI, ML RUL, Digital Twin, NCCL, SPARQL semantic
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.