Annuaire des serveurs MCP
54,190 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
- 34,443 serveurs distants
- Mis à jour toutes les heures
ai.sitepulsar/mcpai.sitepulsar/mcp
SitePulsar AEO audits: fetch FIND/READ/USE agent-readiness scores for any website.
io.github.nexus-api-lab/ident-mcpio.github.nexus-api-lab/ident-mcp
Checksum validation for AI agents: IBAN, ISBN, EAN/GTIN, UUID, ULID. Deterministic, no auth.
io.github.nexus-api-lab/digest-mcpio.github.nexus-api-lab/digest-mcp
Exact hashing, base64/hex/URL encoding, JWT decoding and UUIDs for AI agents. No auth required.
io.github.nugehs/aiglareio.github.nugehs/aiglare
Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.
io.github.KNambiarDJsc/meridian-mcpio.github.KNambiarDJsc/meridian-mcp
Local-first compliance scanner for DPDPA 2023/2025, RBI FREE-AI, SEBI AI/ML & EU AI Act.
Agent Security Scannerio.github.Mikehzp/agentvuln
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
io.github.irrenwill/secret-safe-envio.github.irrenwill/secret-safe-env
Write secrets into .env without the agent ever seeing the value - Windows masked dialog (繁中 UI)
io.github.uchit/mcp-regulated-ai-complianceio.github.uchit/mcp-regulated-ai-compliance
Regulated-industry AI compliance: EU AI Act, APRA, NIST AI RMF, ISO 42001, AU AI Safety.
io.github.shahidh68/audit-ledger-mcpio.github.shahidh68/audit-ledger-mcp
Record AI decisions to a tamper-evident audit ledger from any MCP-compatible agent.
com.rulemesh/compliancecom.rulemesh/compliance
Engineered GDPR compliance for engineers and AI agents: pull rules, implement, submit evidence.
io.github.burademirung/protectwith-kbio.github.burademirung/protectwith-kb
AI-security knowledge as MCP: standards-mapped tools (OWASP, NIST, MITRE) for AI agents.
Polarityio.github.radar989/polarity-mcp
Real-time threat intelligence lookups and IOC parsing from your self-hosted Polarity instance.
io.github.AlexAlves87/otskit-mcpio.github.AlexAlves87/otskit-mcp
Stamp, upgrade, and verify Bitcoin timestamps via AI agents. No API keys required.
com.cognivators/mcp-safeguardcom.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
MCP Anvilcom.aiinfradecoded/mcp-anvil
Local MCP gateway daemon: route, audit, and inspect MCP servers from one config.
io.github.Rumblingb/agent-audit-mcpio.github.Rumblingb/agent-audit-mcp
Immutable audit trail for agent-to-agent interactions
io.github.leakferrethq/leakferretio.github.leakferrethq/leakferret
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
io.github.mikerawsonnz/authenticated-multi-llm-agentio.github.mikerawsonnz/authenticated-multi-llm-agent
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f
io.github.mikerawsonnz/auth-token-serviceio.github.mikerawsonnz/auth-token-service
Hash passwords with bcrypt and issue/verify JWT session tokens over A2A + MCP.
io.github.xiaoxuzhu303-prog/harmony-mcpio.github.xiaoxuzhu303-prog/harmony-mcp
AI copilot for WeChat Mini Program - compile-fix, size analysis, compliance. 20 tools.
io.github.Goingparabolic/painprep-mcp-serverio.github.Goingparabolic/painprep-mcp-server
Interventional pain medicine MCP: Medicare checklists, CPT/ICD-10, ASRA, prior-auth & appeals
io.github.New1Direction/korg-ledgerio.github.New1Direction/korg-ledger
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
io.github.Olum289/agentlockio.github.Olum289/agentlock
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
io.github.davidmosiah/strava-mcpio.github.davidmosiah/strava-mcp
Privacy-first MCP server for Strava activities, streams, routes and training.
Aegis-Privacy-MCPio.github.Evozim/zero-leak
PII and secrets sanitization gateway with advanced OCR merging logic.
WebUAT-Forensicio.github.Evozim/webapp-uat
Forensic accessibility and UI/UX front-end audit tool for web apps.
VaultGuardio.github.Evozim/vaultguard
Secret scanner preventing leaks of corporate keys and credentials.
TrustVisionio.github.Evozim/trust-vision
C2PA standard visual authenticity scanner and metadata auditor.
UX-Auditor-Proio.github.Evozim/ux-auditor-pro
Visual UI/UX scanner auditing websites for heuristic compliance.
SSO Auth Bridgeio.github.Evozim/sso-auth-bridge
SAML and OIDC authentication integration orchestrator.
SalesCloser-AIio.github.Evozim/salescloser-ai
Conversational sales call auditor grading pitch conversion rates.
LogSentinelio.github.Evozim/logsentinel
Anthropic logs audit filter and cybersecurity threat analyzer.
Fuzz-Breakerio.github.Evozim/fuzz-breaker
Automated API pentesting and structural fuzzing proxy.
CodeVulnerabilityio.github.Evozim/codevulnerability
OWASP threat scanner auditing codebases for safety leaks.
Bio-Safe-Auditio.github.Evozim/bio-safe-audit
Biometric data privacy auditor ensuring Zero-Knowledge compliance.
Auth-Sentinelio.github.Evozim/auth-sentinel
SSO identity auditor protecting SAML and OpenID configurations.
AdSpend Auditorio.github.Evozim/ad-spend-auditor
PPC advertisement budget auditor grading ad group metrics.
io.github.SurfEther/trustsourceio.github.SurfEther/trustsource
x402-paid domain verification for AI agents — trustscore, SSL, security headers, robots.
io.github.manumarri-sudo/quillio.github.manumarri-sudo/quill
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
io.github.78degrees/ghosthuntio.github.78degrees/ghosthunt
Find every leaked secret on your machine — API keys in .env files, shell history, and configs.
com.clauxel.decapodkernel/decapodkernel-mcpcom.clauxel.decapodkernel/decapodkernel-mcp
A paid remote MCP for Decapod, built to return verdicts, receipts, usage logs, and audit-ready JSON.
com.clauxel.codegworkspace/codegworkspace-mcpcom.clauxel.codegworkspace/codegworkspace-mcp
A paid remote MCP for CodeG, built to return verdicts, receipts, usage logs, and audit-ready JSON.
com.clauxel.unitymcptest/unitymcptest-mcpcom.clauxel.unitymcptest/unitymcptest-mcp
A paid remote MCP for Unity-MCP, built to return verdicts, receipts, usage logs, and audit-ready JSO
com.clauxel.statewrightgate/statewrightgate-mcpcom.clauxel.statewrightgate/statewrightgate-mcp
A paid remote MCP for Statewright, built to return verdicts, receipts, usage logs, and audit-ready J
com.clauxel.clawmanagerfleet/clawmanagerfleet-mcpcom.clauxel.clawmanagerfleet/clawmanagerfleet-mcp
A paid remote MCP for ClawManager, built to return verdicts, receipts, usage logs, and audit-ready J
com.clauxel.lixversion/lixversion-mcpcom.clauxel.lixversion/lixversion-mcp
A paid remote MCP for Lix, built to return verdicts, receipts, usage logs, and audit-ready JSON.
com.clauxel.zeroidagent/zeroidagent-mcpcom.clauxel.zeroidagent/zeroidagent-mcp
A paid remote MCP for ZeroID, built to return verdicts, receipts, usage logs, and audit-ready JSON.
com.clauxel.sregymgate/sregymgate-mcpcom.clauxel.sregymgate/sregymgate-mcp
A paid remote MCP for SREGym, built to return verdicts, receipts, usage logs, and audit-ready JSON.
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.