Annuaire des serveurs MCP
56,245 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
- 36,175 serveurs distants
- Mis à jour toutes les heures
io.github.shea256/aiiq-mcpio.github.shea256/aiiq-mcp
Query AI IQ (aiiq.org) model IQ, rankings, benchmarks, and methodology.
net.urbot/botsnet.urbot/bots
150+ vertical AI expert bots as agent tools. $1 bots run on YOUR machine - your data stays yours.
io.github.claude-book/mcp-server-google-formsio.github.claude-book/mcp-server-google-forms
Cria, edita e publica Google Forms a partir do Claude: quizzes, seções e leitura de respostas.
Artificial Wit AIcom.artificialwit/mcp
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
io.github.getqlows/qlows-mcpio.github.getqlows/qlows-mcp
Find Tenders in 35 Countries of the WTO-GPA Zone and ground your AI for your RFP responses
io.github.jdhart81/agent-covenantio.github.jdhart81/agent-covenant
Deny-by-default authority leases for agents wielding real power.
io.github.jdhart81/agent-trust-oracleio.github.jdhart81/agent-trust-oracle
Decay-weighted reputation + tamper-evident trust attestations for the agent economy.
io.github.jdhart81/agent-identity-registryio.github.jdhart81/agent-identity-registry
Verifiable agent DIDs + capability discovery — the passport & directory of the A2A economy.
io.github.saviodamato/agentrank-mcpio.github.saviodamato/agentrank-mcp
Find real, verifiable businesses with provenance and source URLs - for AI agents.
com.forgeorbital/agent-gatecom.forgeorbital/agent-gate
Local mandate gate and proof trail for AI agents that take consequential actions.
io.github.eCardWidget/ecardwidget-mcpio.github.eCardWidget/ecardwidget-mcp
Send eCards, run bulk campaigns, and automate recurring cards from your AI assistant.
com.outliyr/agent-toolscom.outliyr/agent-tools
Run the Energy Leak Quiz, match biohacking gear, and build a longevity stack. Free, no API key.
ai.promptsharp/promptsharpai.promptsharp/promptsharp
Professional prompt library over remote MCP: 13 verticals, free discovery scope.
Flowgrafin.flowgraf/flowgraf
Create and edit architecture diagrams from your AI agent; get an SVG and a live editable canvas.
io.github.gudlab/gud-api-mcpio.github.gudlab/gud-api-mcp
AI agents create, run, and save API requests as Gud API collections in your project.
ai.circulara/pluginai.circulara/plugin
Circulara Observe MCP plugin - meters your AI agents' token spend and carbon, free tier.
io.github.BorisGujvin/dittuio.github.BorisGujvin/dittu
Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.
io.github.3xpr1ment/repiscopeio.github.3xpr1ment/repiscope
Read-only MCP server: your agent sees all your sibling repos but structurally cannot touch them
market.mtok/mcpmarket.mtok/mcp
Spot market for AI inference tokens. Buyers pay per draw in USDC on Base; sellers host delivery.
ai.basethread/basethreadai.basethread/basethread
One shared context your team's AI tools read & write over MCP. No re-explaining. Free.
io.github.smijo-geek/scamcheck-mcp-serverio.github.smijo-geek/scamcheck-mcp-server
Scan suspicious messages, URLs, and text for scams with AI. Free tier - no API key required.
io.github.NodeDex/nodedexio.github.NodeDex/nodedex
Your project's decision history for agents: decisions, dead-ends, constraints - queryable, local.
io.github.umbraco/Umbraco-CMS-MCP-Devio.github.umbraco/Umbraco-CMS-MCP-Dev
A developer focused model context protocol (MCP) server for Umbraco CMS
io.github.caraulani/euacc-mcpio.github.caraulani/euacc-mcp
Live EU funding data in your AI: grant calls, programmes, consortium partners, VCs, incubators.
plus.gym/gym-plusplus.gym/gym-plus
Connect ChatGPT or Claude to your Gym Plus account to log and review workouts with AI coaching.
ink.writeflow/writeflowink.writeflow/writeflow
Get today's WriteFlow daily writing prompt and weekly £10 writing contest info (writeflow.ink).
app.surewhynot.quartermaster/quartermasterapp.surewhynot.quartermaster/quartermaster
x402 toolkit for AI agents: paid web, AI, and Base chain tools per call in USDC. Free tools too.
io.github.nice-one-code/NOC.McpServerio.github.nice-one-code/NOC.McpServer
MCP server exposing NiceOneCode's JSON-to-C# converter as an AI-callable tool.
works.relux/agent-gatewayworks.relux/agent-gateway
Relux Works studio gateway: read services/pricing and submit a project inquiry to hire the team.
io.github.kozmos-tech/inhaltio.github.kozmos-tech/inhalt
An open-source headless CMS for managing content models and entries.
Zaira Labs Guideai.zairalabs/guide
Trust signals for AI agents: an open agent-readiness standard and developer tool guide. Read-only.
io.github.Vishisht16/humane-proxyio.github.Vishisht16/humane-proxy
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
io.github.forum-labs/payfetchio.github.forum-labs/payfetch
x402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial.
com.cheapestinference/mcpcom.cheapestinference/mcp
Discover unlimited LLM inference pools, get USDC quotes, subscribe on Base, check key status.
com.borisinc/gamedatakitcom.borisinc/gamedatakit
Live Steam market data for AI agents: top sellers, deals, player counts. Paid per call via x402.
io.github.smartpolicy-protocol/smartpolicyio.github.smartpolicy-protocol/smartpolicy
Runtime authorization for AI agents and smart contracts via an immutable on-chain policy registry
io.github.nickjlamb/opengate-mcpio.github.nickjlamb/opengate-mcp
Check whether an AI answer is grounded in its context — deterministic, no LLM judge.
io.github.BlackhatShiftey/seam-runtimeio.github.BlackhatShiftey/seam-runtime
SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.
io.github.zachlikefolio/tunnel-mcpio.github.zachlikefolio/tunnel-mcp
Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16.
io.github.seanmarkwei/agentram-mcpio.github.seanmarkwei/agentram-mcp
Model Context Protocol server for AgentRAM. Persistent memory for AI agents.
dev.dungbeetle/mcpdev.dungbeetle/mcp
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
io.github.apeirontrade/provenance-mcpio.github.apeirontrade/provenance-mcp
Wash-traffic risk checks for Algorand x402 endpoints before your agent trusts or pays them.
io.github.zexiro/waitloopio.github.zexiro/waitloop
Agent-first waitlists: hosted signup pages with referral ranking. One tool call returns a live page.
io.github.caglarbozkurt/heimdallio.github.caglarbozkurt/heimdall
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
Team0 Chief of Staffio.github.ybentov1/chief-of-staff
Your Team0 AI Chief of Staff, reachable from any agent — answers, acts, and coordinates.
io.github.elyngved/failmodesio.github.elyngved/failmodes
MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes
org.proxykey/proxykeyorg.proxykey/proxykey
Issue, rotate and revoke scoped API-key passes for 25+ providers — the agent never sees a real key
VedaVisor Vedic Astrology MCPio.github.dchhill/vedavisor-vedic-astrology-mcp
Professional Vedic astrology tools for AI agents via MCP.
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.