Annuaire des serveurs MCP
54,128 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
- 34,384 serveurs distants
- Mis à jour toutes les heures
com.hirosecure/agentscom.hirosecure/agents
Programmatic control of the Hiro security platform: scans, tasks, plans, and approvals.
pl.piszczek/ai-economicspl.piszczek/ai-economics
12 calculators for AI cost, energy and agent verification. Free API, no key.
io.github.BlackBoxEngineering/agent-envelope-mcpio.github.BlackBoxEngineering/agent-envelope-mcp
Neutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.
io.github.honeycrisp-suite/mailio.github.honeycrisp-suite/mail
Apple Mail over MCP: fenced reads, draft-only writing, human-gated actions, audited with undo.
io.github.forkflux/forkflux-mcpio.github.forkflux/forkflux-mcp
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
io.github.IsaiahDupree/storebridge-mcpio.github.IsaiahDupree/storebridge-mcp
Remote MCP connector for App Store + Google Play data via StoreBridge API. No auth required.
DataNexus MCPcom.datanexusmcp/mcp-server
Public data intelligence for AI agents — CVE, compliance, patents, contracts, domains.
net.streamfront/jp-addressnet.streamfront/jp-address
Normalize and verify Japanese postal addresses into structured fields for agents.
exchange.carso/carso-exchange-engineexchange.carso/carso-exchange-engine
AI-native platform: cybernetic freight agents transact, verify, find services. Get verified leads.
Melvea Local Honey Discoverycom.melvea/local-discovery
Citation-backed honey producer discovery by place or varietal. Free, no auth.
io.github.VladUZH/sidclaw-governance-mcpio.github.VladUZH/sidclaw-governance-mcp
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
io.github.KN0WBOT/clavisio.github.KN0WBOT/clavis
Encrypted credential vault for AI agents — auto OAuth refresh, rate limiting, audit logging.
io.github.jonnybottles/patch-tuesdayio.github.jonnybottles/patch-tuesday
Query Microsoft Patch Tuesday security updates (MSRC) with EPSS and CISA KEV enrichment
tech.novtriq/engineeringtech.novtriq/engineering
27 engineering compliance and calculation tools for the built environment (UK, EU, UAE).
ai.boundaryai/boundaryaiai.boundaryai/boundaryai
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
io.github.contentfactory/eu-verifyio.github.contentfactory/eu-verify
European business verification for AI agents: registry, VAT, sanctions, IBAN. Pay-per-call x402.
io.github.jaimenbell/rails-mcpio.github.jaimenbell/rails-mcp
Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).
io.github.ipezygj/numguardio.github.ipezygj/numguard
Verify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.
io.github.oromi-uk/oromi-agent-servicesio.github.oromi-uk/oromi-agent-services
25 pay-per-call UK data & verification tools for AI agents. x402 USDC on Base; free quote mode.
io.github.ipezygj/agent-guardio.github.ipezygj/agent-guard
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
com.gocosmik/cosmikcom.gocosmik/cosmik
Live space data for AI agents - rocket launches, ISS passes, launch news. Free, no auth.
io.github.Prismor/prismix-status-mcpio.github.Prismor/prismix-status-mcp
Real-time status for 75+ AI services (OpenAI, Anthropic, Cursor). No auth, CORS-enabled.
GeezerKeeper Referral Exit Routes and Deadlinescom.geezerkeeper/referral-exit-routes
Read-only senior-care exit routes, duplicate-referral deadlines, and templates; no PII or sending.
com.correctover/mcp-servercom.correctover/mcp-server
MCP runtime security. 22µs validation, 97% self-healing. Detects RCE, SSRF, credential hijacking.
ai.atlasverified/atlas-mcpai.atlasverified/atlas-mcp
AI-powered organic supply chain verification: certification, OFAC, FDA import checks.
com.oksigenia/checker-mcpcom.oksigenia/checker-mcp
Domain security & privacy checker as an MCP server. 17 live checks, 0-100 score, local-first.
io.github.oathlayer/oathlayerio.github.oathlayer/oathlayer
Verify AI outputs against real sources. Returns a trust signal and permanent doc number.
io.github.useotterkit/otterkitio.github.useotterkit/otterkit
Tunnels and webhooks for AI agents: capture, await, verify, replay, and send signed test events.
dev.mcpgrade/mcpdev.mcpgrade/mcp
Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev
com.secdim/mcpcom.secdim/mcp
Personalised developer security learning pathways from SecDim's challenges and courses.
io.github.thomasxm/crowdsentinel-mcp-serverio.github.thomasxm/crowdsentinel-mcp-server
AI threat hunting & incident response for Elasticsearch/OpenSearch with endpoint & network forensics
io.github.Braynexservices/nigeria-nigsac-sanctionsio.github.Braynexservices/nigeria-nigsac-sanctions
Screen a name vs Nigeria's NIGSAC sanctions register. Best-effort signal, not compliance-grade.
io.github.eidetic-works/nucleusio.github.eidetic-works/nucleus
Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.
io.github.threadlinqs-cmd/intelthreadlinqs-mcpio.github.threadlinqs-cmd/intelthreadlinqs-mcp
Threadlinqs threat-intelligence MCP — 49 tools: threats, detections, IOCs, actors, C2, MITRE, CVEs
io.github.Raffaele86/local-leads-mcpio.github.Raffaele86/local-leads-mcp
Find local businesses with no website via OpenStreetMap, then verify them. No API keys needed.
io.github.dhanushs1912-svg/agent-receipts-mcpio.github.dhanushs1912-svg/agent-receipts-mcp
EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
com.watchtower-api/sanctions-screeningcom.watchtower-api/sanctions-screening
Sanctions screening, KYB, identifier validation, jurisdiction risk & secret scanning for AI agents
com.saasdossier/evidence-ledgercom.saasdossier/evidence-ledger
Read-only MCP: free OpenAI security evidence ledger (55 fields) + SaaSDossier release register.
za.co.zaroniacalculator.api/verifyza.co.zaroniacalculator.api/verify
Independent ZARONIA coupon verification for SA FRNs & money-market paper, SARB-compounded index.
dev.pullboard/pullboarddev.pullboard/pullboard
Coordination board for AI agents: atomic claims, no self-verification, independent verify-gate.
io.github.Correctover/correctover-mcp-serverio.github.Correctover/correctover-mcp-server
Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.
io.github.Postcept/mcpio.github.Postcept/mcp
Verify agent actions against the system of record and get signed completion receipts.
io.github.Toby-Self/asymptotic-ethicsio.github.Toby-Self/asymptotic-ethics
MCP server for an Asymptotic Ethics governance simulation with a verified compliance oracle.
io.github.Toby-Self/federated-ai-commonsio.github.Toby-Self/federated-ai-commons
MCP server for a federated AI-commons governance simulation with a verified compliance oracle.
io.github.zerozaky/spoilerio.github.zerozaky/spoiler
Sealed prediction-market verdicts, graded in public across Polymarket and Kalshi. No auth required.
io.github.closermethod/outreach-deliverability-mcpio.github.closermethod/outreach-deliverability-mcp
Channel-safety for cold outreach: volume limits, SPF/DKIM/DMARC, spam-trigger auditing.
io.github.rijul170/sophos-central-mcpio.github.rijul170/sophos-central-mcp
MCP server for Sophos Central — endpoint security, XDR/MDR, and MSSP multi-tenant ops
io.github.jdhart81/quantity-takeoffio.github.jdhart81/quantity-takeoff
Auditable construction takeoffs with locked waste and conservative purchase rounding.
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.