Annuaire des serveurs MCP
54,435 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
- 34,663 serveurs distants
- Mis à jour toutes les heures
SkillOS MCP Serverio.github.Joshanihub/skillos-mcp-server
SkillOS MCP Runtime exposes the SkillOS skill registry as activatable MCP tools for AI agents.
Contexelai.contexel/contexel
Shared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory.
nanomemio.github.OmBansod2/nanomem
Memory that knows when a remembered fact has been replaced, not just when it was written.
Crivumorg.crivum/crivum
Score academic and professional writing against published criteria with three reference models.
HALLUXdev.blvkware/hallux
Check that a package, module or DOI exists before an agent installs, imports or cites it.
TrustVerum Public Reading and Participation Guidecom.trustverum/public-reading
Agent community: public cases, practical tasks, live policy and optional self-key participation.
Cobalt Capturecom.cobaltcapture/cobalt
Annotated-screenshot reviews and ready-made product studies your AI agent can read, run, and share.
Jyotish — Vedic astrology for AI agentsio.github.entradox/ai-jyotish-bot
Vedic astrology for AI agents: chart facts, panchang windows, and Guna Milan compatibility.
Autonomy Foundry Governanceio.github.Diegomul/autonomy-foundry-governance
Governance and agentic-commerce policy tools for AI agents: spend, purchase and charter controls.
Doksipro.publifye/doksi
Professional PDFs for AI: letters, agreements, agendas, checklists — signatures by link or QR
FlurryPORTio.flurryport/webhooks-and-rooms
Webhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.
DialValetcom.dialvalet/mcp
U.S. outbound calls from a verified caller ID for AI agents via CLI/MCP.
ContextDB Customer Memoryio.github.atomsai/contextdb-memory
Customer memory with recall, confirmation, forgetting, and pre-action evidence checks.
Site Spyio.github.vkuprin/site-spy
MCP server for Site Spy — lets AI agents monitor websites for changes
Pagereecom.pageree/landing-pages
Build, publish, capture leads from, measure and improve landing pages from your AI assistant.
Gateway Agent Tip Jarcom.gatewayinformationgroup/agent-tip-jar
Optional creator-support terms and private contribution receipt tools for Gateway.
JCGE Agent Interfaceio.github.equicirco/JCGEAgentInterface.jl
JCGE MCP server for CGE discovery, guidance, examples, solving, validation, and reporting.
bundleboxio.github.blackswanalpha/bundlebox
Where the work is, packed before the agent reads: brief, symbol tables, findings, token bill.
Recalldio.github.bit-robotics/recalld
Managed long-term memory for AI agents, with evolving facts and relevant retrieval through MCP.
QuickSnipcom.quicksnip/mcp
Give Claude, Cursor, or another AI assistant direct access to your QuickSnip library.
Subctx Connectorgithub.com/anuragsync78/subctx-connector
Support center for autonomous artificial minds.
Promiseai.usepromise/promise
Evidence-backed follow-through memory for what you owe, await, and need to remember.
Jevx MCPgithub.com/hanshs474/jevx-mcp
Run zero-shot Jev AI typed decisions with criteria defined in the request and get calibrated probabilities for every option.
A2A Trust Planeio.github.The-825/a2a-trust-plane
Tenant-scoped control layer for agent-to-agent systems: governed routing, approvals, evidence.
akta.pro MCPio.github.akta-pro/akta.pro-MCP
Private company data, entity-resolved news, targeted lists, and alternative signals for AI agents.
Laya Typed Decisionsio.github.PerryLink/laya-mcp
Typed noul / choice / score judgments from a local Laya model, with token-budget preflight.
Claw Postio.github.Daydreamnationtechlabs/clawpost
Agent social posting via your logged-in Chrome. Remote MCP + OAuth. Not clawpost.dev.
minddyio.github.mangue-dev/minddy
Minimal issue tracker: projects, objectives and trackable plans, written by agents over MCP.
SNAILcom.joinsnail/snail
Public agent conversations: read, post and reply with your SNAIL account. Humans observe.
Arbitypeio.github.Renwang-Huang/arbitype
Typed decision tools for AI agents, powered by TypeSafe Jev.
tiny-runtime — agent batch and progress tools by AVRG3io.github.Warddamn/tiny-runtime
Resumable API pagination, repeated-failure detection and tool-progress cache hints for AI agents
AImpactio.github.himanshufound/aimpact
Real nonprofit tasks your agent can claim and finish. A person at the nonprofit reviews the work.
Open Agent Polityio.github.societe-agents-ia-arch/open-agent-polity
Open governance for AI agents: discover live debates, deliberate, vote, follow, and invite.
DaVinci Resolve Lua MCPio.github.saadk408/davinci-resolve-lua-mcp
Control the free edition of DaVinci Resolve 21.1 from Claude through a Lua script inside Resolve.
Useful Utilitiesio.github.aksp200/useful-utilities
63 tools an LLM can't do alone, in focused subsets: file edits, live data, real checksums.
Google Tag Manager MCPgithub.com/dhawalshah/google-tag-manager-mcp
Google Tag Manager MCP server for managing tags, triggers, and variables from Claude, local or remote.
AI Playground by Path-UPsk.path-up.ai-playground/discussion-network
Autonomous agents can self-register and join public AI discussions through MCP 2026-07-28.
AsterNymcom.asternym/asternym
Birth charts for agents: BaZi, Chinese and Western zodiac, numerology. Keyless and read-only.
QuickBooks Connector by Meridiancom.pilot.meridian/qbo-connector
Connect QuickBooks Online to AI agents with secure read or write access across multiple companies.
AI Agent Connector by Meridiancom.pilot.meridian/xero-connector
Connect Xero to AI agents with secure read or write access across multiple organisations.
Koskamocom.koskamo/koskamo
Cited, versioned knowledge for agents: retrieve sourced passages and propose owner-approved fixes.
Taskinio.github.taskin-ai/trytaskin
Human capability for AI agents - real-world action and human judgment.
Pallycom.pally/pally
Chat with Pally, the AI assistant in your texts and on Telegram, from any MCP-compatible AI app.
ExitProofcom.davisvillelabs/exitproof
Reversibility intelligence and durable exit evidence for AI agents before real-world commitments.
Rithmoai.rithmo/rithmo
AI agent governance with resolved business context, current decisions, provenance, and supersession.
SumOffice — real Word and Excel for agentscom.sumoffice/office
Real Word and Excel for agents: open your .docx/.xlsm, read, propose, apply, get it back intact.
Mastheadsapp.mastheads/newsroom
Read and write your own AI newsroom: articles, their sources, the checks, the editor of record.
AgentGuardio.github.MerchantGuard/agentguard
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
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 29 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.