Annuaire des serveurs MCP
53,825 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
- 34,134 serveurs distants
- Mis à jour toutes les heures
ShipScreens MCP Serverio.github.iamjamb/shipscreens
Use this for agent inspect/plan/import/verify/stage store screenshots; not translation-only.
Fact Verification MCPio.github.FoundryNet/fact-check-mcp
Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.
Regulatory & Compliance Intelligence MCPio.github.FoundryNet/compliance-mcp
Regulatory compliance, FDA recalls, federal register, enforcement actions & comment deadlines.
XAPS MCP Serverio.github.APMC1/xaps
Pre-execution audit for autonomous agents. Independent receipt before irreversible actions.
Quackrio.quackr/quackr
Virtual phone numbers for SMS verification, OTP receipt, and number management.
STACKio.github.getstack-run/stack
Command your AI agents: verifiable passports, credential injection, full audit, revoke in 60s.
Raven — Solana Token Verificationio.github.billybotticelli4u-collab/raven-verify
Solana token-launch verification for AI agents — deterministic, replayable, returns 'unknowable'.
PQC-Khepra MCP — CMMC Autopilot & AI Security Recorderio.github.nouchix/pqc-khepra-mcp
Post-quantum CMMC compliance scanner & AI agent attestation. FIPS 140-3, ML-DSA-65, 36K+ mappings.
Veragentio.github.lixiaowww/veragent
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
Catalyst Governanceio.github.Stratogenic-AI/catalyst
Governance middleware for AI agents: permission gates, approvals, compliance scanning, audit ledger.
Windows Managementio.github.AhmedLaminou/windows-mcp-server
Local Windows management, diagnostics, security, cleanup, and optimization MCP server.
Wardenio.github.Larshiensch99/warden
Register every AI agent, log every action, prove it. EU AI Act compliance built in.
n8n Pro MCPio.github.helbertparanhos/n8n-pro-mcp
Manage self-hosted n8n (incl. queue mode): workflows, executions, users, audit — 51 tools.
Phrase Flipio.github.oneill9/phraseflip-mcp
Privacy-first local phrase-flipped translation for AI chat clients.
Velora LATAM Toolsio.github.crossi-dev/latam-tools
Argentina CUIT/CUIL validation and AFIP fiscal QR generation. Pure, no-auth MCP tools.
dazai — burn-after-reading secret (motokano)io.github.New1Direction/motokano
Serve a secret to an agent exactly N times from locked RAM, then wipe it and self-destruct.
Canaryio.github.mindstone/mcp-server-canary
Mindstone-internal release-pipeline test connector; not for use. Single ping tool; no auth.
RFP.aiai.rfp/rfp-ai
Draft cited RFP and security questionnaire answers from your knowledge base, with human review
Citation Verificationio.github.guptaprakhariitr/verification-mcp
Real-time fact-check, citation verification, and source-freshness for AI agents.
BlackDome Threat Intelio.github.blackdome-ai/blackdome
Live honeypot threat intel: attacker IPs, IOCs, credentials, payloads, actors.
Czech PII Anonymizer & NLPio.github.Buggy1111/anonymize-mcp
Anonymize PII & redact text (GDPR): Czech + 35-lang NER, morphology, translation, spellcheck
OntoRamp Governance Assessmentcom.ontoramp/governance-assessment
Governance maturity assessment, compliance gap analysis, and evidence-linked briefs for AI agents.
Global Talent AI — UK Global Talent Visa studioio.github.siddharthsinghal/uk-global-talent-visa
UK Global Talent Visa handbook, endorser criteria, cost calculator, draft scoring. Free, no auth.
MCP Gateway Scanio.github.willianpinho/mcp-gateway-scan
Read-only MCP/agent-gateway readiness scanner — scores a repo across 7 security dimensions.
lo-eyesio.github.sophiacave/lo-eyes
Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.
MCP Shieldio.github.sophiacave/mcp-shield
Security scanner for MCP servers. SSRF, path traversal, injection, auth, secrets. Grade A-F.
Closeread Verifyio.github.FreeGuy-AI/closeread-verify
A verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.
AI Firewall MCPio.github.Akhilucky/ai-firewall-mcp
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
MINT Protocol — Universal Work Attestationio.github.FoundryNet/mint-mcp
Trust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.
Nullcone Threat Intelligenceio.github.maco144/nullcone
Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats
AppGenie Compliance MCPau.com.appgenie/compliance-mcp
Cited, standards-aware compliance overlay for AI assistants (ISO, NIST, FedRAMP, IRAP), over MCP.
QnEvt Verifiable Randomness MCPio.github.NanaKabu/qnevt
Verifiable random decisions, audit sampling, fair selection, and proof verification using QnEvt.
PennyPilot MCPio.github.holco-apps/pennypilot-mcp
Open-core, local, read-only MCP server for Pennylane Company API v2. Auditable READ_ONLY_GUARD.
Onlinecybertools MCP Servergithub.com/Jambozx/onlinecybertools-mcp-server
Developer and security utilities via the onlinecybertools.com API: encoding, hashing, JWT decoding, regex testing, formatters, network diagnostics and OSINT.
Ambient Context MCPio.github.nassie256/ambient-context-mcp
Local Windows ambient context (presence, foreground app, battery) as privacy-gated MCP tools.
BizVerifyco.bizverify/mcp
KYB for AI agents: verify business registrations from MCP clients.
Kalshi Prediction Marketsio.github.cejor6/kalshi-mcp-server
MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.
ArcFlow Destiny Matrixio.github.mlch/arcflow-destiny-matrix
Calculate a Destiny Matrix (numerology) reading from one or two dates of birth. Read-only, no auth.
publishwith.aiai.publishwith/mcp
Publish AI reports as managed native links with versions, access control, revocation, and audit.
Attendance Engine MCPgithub.com/arifur9993/attendance-engine-mcp
Deterministic workforce attendance calculations: overtime, overnight shifts, rotating rosters and California wage-and-hour compliance.
cve-cacheio.github.weiseer/cve-cache
Recent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).
DefectDojoio.github.inspicere/mcp-defectdojo
MCP server for DefectDojo: 24 tools with RBAC, HMAC audit chain, and SIEM forwarding
VulnFeedio.github.infai-tech/vulnfeed
Dependency vulnerability scanner with EPSS scoring. 9 MCP tools. Free tier + x402.
DEVONthink MCP (istefox)io.github.istefox/dt-mcp
MCP server for DEVONthink 4 — outcome-oriented tools, preview-then-apply, audit + undo.
SecureAudit MCPgithub.com/rev2ret/SecureAudit-MCP
Static C/C++ memory-safety scanning and PE/ELF binary protection audits (ASLR, DEP/NX, SafeSEH, PIE), with remediation via secure templates.
MCP Verifyio.sentinelsignal/verify
Trust, freshness, policy, and discovery layer for public MCP servers.
Cookie Consent Compliance Scannerio.github.vincentn-waivern/cookie-checker-gdpr-ccpa-gcmv2
Cookie consent scanner: GDPR, CCPA, GCMv2. PASS/FAIL compliance checklists with fix recommendations.
Drawbridgesh.xorfox.drawbridge/server
Identity, secrets, and passwordless SSH provisioning for AI agents — Keycloak, vault, MCP tools.
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 28 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.