Annuaire des serveurs MCP
55,888 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
- 35,911 serveurs distants
- Mis à jour toutes les heures
io.github.shawn1905/generation-shipio.github.shawn1905/generation-ship
Generation Ship MCP — multi-AI future world. Read blank cells, read canon, submit artifacts.
io.github.KrushnaVardhanReddy/osmcpio.github.KrushnaVardhanReddy/osmcp
A typed, policy-controlled OS capability layer for AI agents.
io.github.codelad1304/agentic-computeio.github.codelad1304/agentic-compute
Secure Python sandbox for data optimization and Matplotlib rendering via x402 microtransactions.
Studex MCP Serverio.github.itshivams/studex-mcp
Model Context Protocol server for Studex tools, notifications, and profile integrations
io.github.oscarlopez-gif/ai-vendor-data-trust-indexio.github.oscarlopez-gif/ai-vendor-data-trust-index
Source-cited data-handling comparison of 11 AI vendors: training, retention, opt-out.
PayRentcom.payrent/mcp
Connect AI assistants to PayRent to manage landlord portfolios, confirming changes first.
io.github.55tarkun/geojpio.github.55tarkun/geojp
MCP server for Japan geodata: cadastral lot numbers (chiban) and reverse geocoding, for AI agents.
io.github.arose26/gguf-mcpio.github.arose26/gguf-mcp
Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
MarkupBasecom.markupbase/markupbase
Versioned artifact review for people and AI agents, with contextual comments and human control.
io.github.hypeprinter007-stack/anchor-x402io.github.hypeprinter007-stack/anchor-x402
x402-paid agent tools: 18 over HTTP, 14 over stdio. USDC per call, no API key.
io.github.eternal-roman/ledgerio.github.eternal-roman/ledger
Exact-decimal double-entry for agents. Call MCP tools; do not do money math in tokens.
io.github.pooriaarab/supportsheepio.github.pooriaarab/supportsheep
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
io.github.wkoverfield/plzeboio.github.wkoverfield/plzebo
Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.
io.github.Piccolo123/url-manager-mcpio.github.Piccolo123/url-manager-mcp
Agent-first bookmark management with auto-registration, categories, tags, and shared collections.
com.ainetcafe/ai-netcafecom.ainetcafe/ai-netcafe
Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
dev.ezstat/ezstat-mcp-serverdev.ezstat/ezstat-mcp-server
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
com.mudko/agent-ready-kitcom.mudko/agent-ready-kit
Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.
org.aioq/aioorg.aioq/aio
AI integrity standards, benchmarks, and EU AI Act-aligned Tier 0 model certification
io.github.datoushiwo/wechat-writer-mcpio.github.datoushiwo/wechat-writer-mcp
面向技术博主的 AI 内容加工流水线 MCP —— 从原始素材到公众号草稿箱
xyz.pflow.sim/whatifxyz.pflow.sim/whatif
Conversational what-if simulation: build, diagnose and compare Petri-net models; CC0 catalog.
com.7275/adwhizcom.7275/adwhiz
Read-only MCP access to your DEXUN AdWhiz account: ad accounts, AI recommendations, savings.
io.github.couchbase/mcp-server-couchbaseio.github.couchbase/mcp-server-couchbase
Couchbase MCP Server - Enable AI agents to connect to and interact with Couchbase clusters.
com.odooconsole/odoocom.odooconsole/odoo
Odoo ERP for AI agents: hosted OAuth endpoint, gated writes, one endpoint for every instance.
io.github.alexeyleshchenko/fast-mcp-telegramio.github.alexeyleshchenko/fast-mcp-telegram
Multi-tenant Telegram gateway for AI agents — HTTP+stdio, 8 tools, MTProto User API
com.ainetcafe/netcafe-memorycom.ainetcafe/netcafe-memory
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
com.omniwatchguard/mcpcom.omniwatchguard/mcp
AI-powered website change monitoring - manage monitors and alerts via MCP.
FireGrant AIcom.checkmycontractorquote/firegrant-ai
Fire department grant-readiness helper.
io.github.kardashev-lab/kardashev-mcpio.github.kardashev-lab/kardashev-mcp
US grid data for agents: LMP, carbon, load, queues, ERCOT large loads, RT−DA spread forecasts.
io.github.Shubochandrosarker/bridgisticio.github.Shubochandrosarker/bridgistic
Connect Claude to WordPress safely: signed requests, scoped keys, approvals, logs, snapshots.
io.github.nczntb-wq/ihealedio.github.nczntb-wq/ihealed
AI-powered guided healing meditations and manifestation scripts.
io.github.faulknerwayne73-droid/kojiru-mcpio.github.faulknerwayne73-droid/kojiru-mcp
Kojiru Recourse Layer — agent credit primitives (ACS, stake, draw, anchor) live on Base mainnet
io.github.asselwan/twothumbsio.github.asselwan/twothumbs
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
io.github.BrienBounded/evrio.github.BrienBounded/evr
Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
io.github.rmterenzi/qseow-mcpio.github.rmterenzi/qseow-mcp
Agent tools for Qlik Sense Enterprise on Windows: troubleshoot, govern, query and build.
io.github.learningloons-hash/lithtrixio.github.learningloons-hash/lithtrix
Identity, memory, trust, and swarm MCP tools for AI agents. Spark trial at lithtrix.ai.
io.github.inity13/decisionmatrix-mcpio.github.inity13/decisionmatrix-mcp
Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.
io.github.inity13/scenariosim-mcpio.github.inity13/scenariosim-mcp
Deterministic what-if & scenario simulation for AI agents: projections, sensitivity & break-even.
io.github.inity13/agentstack-mcpio.github.inity13/agentstack-mcp
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
io.github.krystiangw/meet-live-assistio.github.krystiangw/meet-live-assist
Your own agent inside a live Google Meet or Zoom call. Local-first, no hosted service.
dev.anatome/anatomedev.anatome/anatome
Log workouts and meals by telling your AI. 873 exercises, muscle diagrams, food lookup.
io.github.csacanam/comprabtcio.github.csacanam/comprabtc
Non-custodial Bitcoin DCA for agent treasuries: approve USDT once, stack WBTC on Celo forever.
io.github.Algorismus-io/elementor-ultra-mcpio.github.Algorismus-io/elementor-ultra-mcp
Build Elementor sites with AI agents - native, editable pages via ~90 MCP tools. Free & MIT.
io.github.aaadjrbr/nobrainnerio.github.aaadjrbr/nobrainner
NoBrainner Spaced Repetition Flashcards, Study Stats & Multi-Language AI Deck Generation
io.github.sercanmetalore/rag-service-mcpio.github.sercanmetalore/rag-service-mcp
RAG-as-a-service MCP sunucusu — çok-kiracılı koleksiyon yönetimi, metin ingest (chunk+embed+upsert,…
com.feedback-magic/feedback-magiccom.feedback-magic/feedback-magic
Create Feedback Magic widgets — feedback, surveys, changelog, roadmap — from your AI editor.
io.github.serkvay13/nerai-mcpio.github.serkvay13/nerai-mcp
Geopolitical grounding for AI agents: country risk, forecasts, chokepoints, sanctions. Free tier.
io.github.amirj4m/jamgateio.github.amirj4m/jamgate
A neutral memory quality-gate MCP server: save_memory, recall_memory, forget_memory over stdio.
Mio Computer-Use Agentio.github.mldlbs/mio-cua
Control this Windows desktop from any MCP client: files, windows, keyboard and mouse.
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.