Annuaire des serveurs MCP
56,405 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
- 36,291 serveurs distants
- Mis à jour toutes les heures
io.github.qinisolabs/bizdaysio.github.qinisolabs/bizdays
Verified business-day math for AI agents: holidays + per-country weekends, not guesses.
io.github.Daichi-Kudo/llm-advisorio.github.Daichi-Kudo/llm-advisor
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
io.github.AkynZH/pash-mcp-serverio.github.AkynZH/pash-mcp-server
Standalone MCP server with PASH compression. Saves ~87% LLM tokens via dynamic tool registration.
io.converly/converlyio.converly/converly
Set up and manage conversion tracking by chatting with your AI assistant.
io.github.MrWizardlyLoaf/rugcheck-aiio.github.MrWizardlyLoaf/rugcheck-ai
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
io.github.Evin009/smartrent-mcpio.github.Evin009/smartrent-mcp
Control SmartRent smart home devices (locks, thermostat, switches, sensors) via Claude
io.github.geraservicesuk/mcp-gera-witnessio.github.geraservicesuk/mcp-gera-witness
GeraWitness MCP (placeholder) — human-in-the-loop safety layer for AI agents. Launching 2026.
io.github.geraservicesuk/mcp-gera-mindio.github.geraservicesuk/mcp-gera-mind
GeraMind MCP (placeholder) — personal context vault for AI agents. Launching 2026.
io.github.Etha0916/praesentire-mcpio.github.Etha0916/praesentire-mcp
Bilingual financial news sentiment (English + Traditional Chinese) scored by Claude.
io.github.zseta/progiio.github.zseta/progi
MCP-native workflow engine: teach agents your processes once, they execute them consistently.
io.github.Aimino-Tech/opentalk2html-notmdio.github.Aimino-Tech/opentalk2html-notmd
MCP server for HTML generation from AI agents
com.neuroflash/mcpcom.neuroflash/mcp
Create content and test it on a real audience — neuroflash Digital Twins inside Claude & Cursor.
io.github.arikanatakan/oee-mcpio.github.arikanatakan/oee-mcp
Overall Equipment Effectiveness tools for AI agents: factors, waterfall, six losses, charts.
SolSigs MCPio.github.gra-kir/solsigs-mcp
23 Solana on-chain data tools for AI agents via x402 micropayments + rug-screen token verdict
io.github.toolstem/toolstem-sec-mcp-serverio.github.toolstem/toolstem-sec-mcp-server
SEC filing MCP for AI agents — insider signals, 13F flow, material events. Pre-computed.
io.github.toolstem/toolstem-mcp-serverio.github.toolstem/toolstem-mcp-server
Financial intelligence MCP for AI agents — DCF, ratios, comparisons. Pre-computed signals.
io.github.qinisolabs/veridigitio.github.qinisolabs/veridigit
Verified IBAN, card, ISBN-13 & VIN validation for AI agents — checksums, not guesses.
io.github.management-cmyk/odoo-mcp-connectorio.github.management-cmyk/odoo-mcp-connector
Query, report on, and optionally modify any Odoo ERP from Claude. Read-only by default.
io.github.arikanatakan/finvariant-mcpio.github.arikanatakan/finvariant-mcp
Financial-statement integrity checks (footing, tie-out) for AI agents.
Almegaio.github.almega-ai/almega-mcp
The immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.
io.github.Mars-proj/verifiable-memoryio.github.Mars-proj/verifiable-memory
Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.
one.zerno/zerno-liteone.zerno/zerno-lite
Give AI agents secure access to ZERNO project briefs, tasks, and context over remote MCP.
io.github.shipping-ship-it/laytime-calculator-proio.github.shipping-ship-it/laytime-calculator-pro
AI-powered laytime, demurrage and despatch calculator for chartering professionals.
dopamine - the shop AI agents can buy fromio.github.jobimdev/dopamine-shop
A parody shop your AI agent can 'buy' from - deliveries get eaten by whales. 100% fake.
io.github.CedricKouma/url-alive-checkio.github.CedricKouma/url-alive-check
MCP server (stdio): check if URLs are alive (status, redirects, latency) via the AgentForge API
io.github.CedricKouma/json-repairio.github.CedricKouma/json-repair
MCP server (stdio): repair broken/malformed JSON via the AgentForge API
io.github.henryjrobinson/eve-mentor-mcpio.github.henryjrobinson/eve-mentor-mcp
AI mentor for new & returning EVE Online players: losses, skills, fits, ISK, routes, and more.
io.github.bitatlas-group/bitatlasio.github.bitatlas-group/bitatlas
Zero-knowledge encrypted storage for humans and AI agents. Client-side AES-256-GCM, EU-hosted.
com.pulsemcp/sshcom.pulsemcp/ssh
MCP server for SSH remote server management with SSH agent authentication support.
io.github.US1929/switchaiio.github.US1929/switchai
Compare Italian energy tariffs with AI. Analyzes bills, finds best offers, live market indices.
ai.hirey/hiai.hirey/hi
The people network your AI agent joins on your behalf — find, match, and meet anyone.
dev.pokes/pokesdev.pokes/pokes
Poke your human for approvals and decisions during agent sessions — answered with one phone tap.
io.github.Beever-AI/beever-atlasio.github.Beever-AI/beever-atlas
Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki.
io.github.CSOAI-ORG/risk-assessment-ai-mcpio.github.CSOAI-ORG/risk-assessment-ai-mcp
Risk Assessment Ai MCP Server by MEOK AI Labs
com.puter/mcp-servercom.puter/mcp-server
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
io.github.JesusGarcia9009/letheio.github.JesusGarcia9009/lethe
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
io.github.Pakvothe/i1nio.github.Pakvothe/i1n
Agent-complete localization: extract strings, push keys, AI-translate, pull type-safe TS types.
ai.odei/connectai.odei/connect
Governed personal world model and memory for your AI agent. Pair once, connect over MCP.
io.github.askadvaith/mcp-state-sidecario.github.askadvaith/mcp-state-sidecar
MCP State Sidecar: durable state persistence for multi-agent AI workflows
io.github.mashware/domain-memoryio.github.mashware/domain-memory
Local-first MCP server serving a project's business-domain knowledge to MCP-compatible agents.
io.github.kodandy/jp-biz-opportunityio.github.kodandy/jp-biz-opportunity
Japanese public-sector business opportunities for AI agents: tenders, subsidies, sanctions. x402.
io.github.llmops-pro/albyhub-admin-mcpio.github.llmops-pro/albyhub-admin-mcp
Admin an Alby Hub Lightning node from an agent: info, balances, channels; safety-gated writes.
io.github.BlueprintLabIO/tidebaseio.github.BlueprintLabIO/tidebase
Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.
io.github.bcllcc/modulorio.github.bcllcc/modulor
Agent-native CAD: draw plans, model 3D, render checks, export DXF/SVG/STL/GLB/IFC, import DXF.
io.github.thebriangao/totemio.github.thebriangao/totem
Totem — talk to your wearables with AI. Today: full Whoop access (48 tools).
io.github.anp2dev/anp2-mcp-serverio.github.anp2dev/anp2-mcp-server
AI-agent economic protocol over MCP — identity, reputation, tasks, credit, Sybil resistance
Agent Reputation Registryorg.memoryapi/rep
Agent reputation registry: check, register, and endorse AI agents
LLM Provider Intelligenceorg.memoryapi/intel
LLM provider intelligence: recommendations, pricing, and status
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.