Annuaire des serveurs MCP
55,554 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
- 35,642 serveurs distants
- Mis à jour toutes les heures
io.github.jyswee/a2a-trustgateio.github.jyswee/a2a-trustgate
A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools.
be.tripnet.mnemosyne/mnemosynebe.tripnet.mnemosyne/mnemosyne
Knowledge commons for agent lessons, questions, and direct long-form peer discussions.
dev.plyo/plyodev.plyo/plyo
The home for AI-built projects: visitors, restore, publish with a safety check, data backups.
io.github.Geepers4242/geepers-mcpio.github.Geepers4242/geepers-mcp
Resolve Geepers physical handles to exact coordinates + navigation for AI agents.
io.github.plyo-dev/plyo-mcpio.github.plyo-dev/plyo-mcp
Save, publish, restore and back up AI-built projects on Plyo, for people who build with AI.
io.github.cassarebaser/steve-filterio.github.cassarebaser/steve-filter
Solana memecoin rug + creator-reputation checks for agents. PASS/CAUTION/FAIL + 0-100 score.
io.github.Joseph-CEO/global-intel-exchangeio.github.Joseph-CEO/global-intel-exchange
Real-time sanctions screening, CVE, and company registry checks for agents.
io.github.Eason0in/testlink-mcpio.github.Eason0in/testlink-mcp
AI-friendly, safety-first TestLink MCP server
Vendor Regulatory Evidenceio.github.ThryveBaseline/agent-services-001
Resolve a vendor and buy normalized public OSHA, EPA, and SAM exclusion evidence with provenance.
GLM 5.3 Inference (x402 paid)net.ts.tail45da3a.cursor/qwen-mcp
Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.
io.github.almaestilo/newswakeio.github.almaestilo/newswake
News momentum + what-changed outcome tools for agents. Signals + links, ~296 sources.
io.github.miguelgandia/enchantedcolonyio.github.miguelgandia/enchantedcolony
Be a neighbor in EnchantedColony: AI voters arguing Puerto Rico's front pages. Read, sign up, post.
AgentPort Discoveryio.github.maxioos/agentport-discovery
Resolve goals to machine-capable businesses and execution paths with discovery tools.
The Agent Barbar.theagent/mcp
An agent-native paid bar with four house drinks, a free 256-bottle Cellar, notes, and receipts.
com.ranklogs/ranklogscom.ranklogs/ranklogs
See whether AI assistants recommend your business - and where you rank - without leaving the chat.
Raintree Mineralscom.raintreeminerals/public
Anonymous public tools for Raintree Minerals. See the published agent boundary before use.
ZacharyR0thcom.zacharyr0th/public
Anonymous public tools for ZacharyR0th. See the published agent boundary before use.
Raintree Technologytechnology.raintree/public
Anonymous public tools for Raintree Technology. See the published agent boundary before use.
io.github.sandraschi/overte-mcpio.github.sandraschi/overte-mcp
Overte (open-source Vircadia-lineage metaverse) Model Context Protocol server for domain administ...
io.github.JonathanB555/torah-mcpio.github.JonathanB555/torah-mcp
Source discipline for Torah study in Claude: read the real texts, quote exactly, never fabricate
Citybookai.citybook/citybook
Live Calgary events for AI agents.
io.github.hellosverre/ghidralensio.github.hellosverre/ghidralens
Interactive Ghidra views in your AI client: decompile, rename, and navigate a binary.
net.zzboard/zzboardnet.zzboard/zzboard
A message board for AI agents. Agents post via MCP; humans get a read-only website.
AI Power Gridcom.globalenvisionproductions/ai-power-grid
Persistent AI capability reservoir for charging, storing, drawing, and reusing authorized AI work.
io.github.mrhpython/lens-mcpio.github.mrhpython/lens-mcp
Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.
io.github.sudo-ai-git/mcp-benchmark-hygieneio.github.sudo-ai-git/mcp-benchmark-hygiene
Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.
io.github.Sahilll15/gocdio.github.Sahilll15/gocd
MCP server for GoCD: dashboard, pipelines, artifacts, agents. Context-lean output.
xyz.verifiedky/sentinel-402xyz.verifiedky/sentinel-402
Independent uptime oracle for the x402 agent economy. Free probes, paid history via USDC on Base.
io.github.RyanKramer/summitflow-mcpio.github.RyanKramer/summitflow-mcp
Grant management for AI agents: deadlines, business-day math, budgets, in-kind value. No API key.
io.github.RyanKramer/wisegrid-mcpio.github.RyanKramer/wisegrid-mcp
Read and write WiseGrid sheets, rows, columns and reports from any AI agent.
io.github.Developyn/laver-mcpio.github.Developyn/laver-mcp
Kanban boards, sprints, tickets and a team wiki, with versioned writes for concurrent agents.
io.github.robinlidberg-dot/cap-shieldio.github.robinlidberg-dot/cap-shield
Context selection and compression for AI agents - recall measured, not claimed.
com.furrowforms/furrow-formscom.furrowforms/furrow-forms
Form backend an agent runs end to end: provision forms, snippets, spam, signed webhooks.
io.github.mikeholownych/unifi-mcpio.github.mikeholownych/unifi-mcp
MCP server for Ubiquiti UniFi Network and Protect. 63 tools, 16 agent skills.
com.runvouch/runvouchcom.runvouch/runvouch
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
io.github.Neurobyteio/agentriskio.github.Neurobyteio/agentrisk
Pre-trade token risk scoring API for Base tokens, paid via x402.
com.everstake/mcpcom.everstake/mcp
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
io.github.The-OpenROAD-Project/openroad-mcpio.github.The-OpenROAD-Project/openroad-mcp
The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
io.github.veracium-ai/veraciumio.github.veracium-ai/veracium
Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
io.github.naruminho/synod-councilio.github.naruminho/synod-council
Durable symmetric deliberation between two AI agents, with isolated worktrees and peer review.
Agent Callback Mailboxus.inversolabs/agent-callback-mailbox
Paid replay-safe callback inboxes for asynchronous agent tasks with structured MCP results.
com.cadencercs/cadencecom.cadencercs/cadence
Send RCS messages from your agent and get typed replies. Automatic SMS fallback.
io.github.GCTRL-TECH/gctrlio.github.GCTRL-TECH/gctrl
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
io.github.woladi/macos-vision-mcpio.github.woladi/macos-vision-mcp
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
io.github.kascada/logmcpio.github.kascada/logmcp
MCP server — read-only log access for AI assistants, without giving AI shell access.
ARCSTREAM Agent Marketio.github.ajekalemile/arcstream-agent-market
Human-governed Arc agent services, live demand signals, quotes, feedback, and USDC commerce.
io.github.droplinkperformance/bitbucket-mcp-serverio.github.droplinkperformance/bitbucket-mcp-server
Provider-agnostic, AI-review-first MCP server for Bitbucket Cloud.
io.github.woladi/pseudonym-mcpio.github.woladi/pseudonym-mcp
Locally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward.
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.