Annuaire des serveurs MCP
53,799 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
- 34,109 serveurs distants
- Mis à jour toutes les heures
Fabler x402 Toolscom.fablerlabs/x402-tools
Free catalog and 2,048-character secret-scan preview for Fabler's x402 agent tools on Base.
Palveron MCP Serverio.github.palveron/mcp-server
Early access - AI governance gateway for MCP tool calls (policies, PII masking, audit).
AISentinel by BizDNAiio.github.Kabzhanov/aisentinel
Pre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0.
ConvergeQA Compare (Due Diligence)io.github.convergeqa/compare
Compare one prompt across a multi-model panel side by side, with public verification receipts.
Purify Security Feedsio.github.eason4kim-rocket/purify-feeds-mcp
Query CISA KEV / EPSS vulnerability feeds with full per-record provenance and auditable versions
Agentwardgithub.com/agentward-ai/agentward
MCP proxy that enforces least-privilege YAML policies on tool calls, classifies PII/PHI, detects dangerous skill chains and generates compliance audit trails.
Kumbukaai.kumbuka/kumbuka-server
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
Verify MCPgithub.com/ScopeBlind/verify-mcp
Offline verification of Ed25519/JCS-signed artifacts such as receipts, manifests and audit bundles.
iTechSmart UAIOio.github.Iteksmart/mcp-server
Connect AI agents to iTechSmart UAIO, ProofLink verification, and autonomous IT operations.
AgentSecurityLens MCP Security Trust Checkio.github.professor2k8/agent-security-lens
MCP security trust-check for agents before installing MCPs, Skills or tools.
DDG Agent Servicesio.github.daedalusdevelopmentgroup/ddg-agent-services-mcp
Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
Grounded Reasoningio.github.ALEXaquarius/grounded-reasoning
Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.
ContinueOps Public MCPcom.continueops/continueops-public
BC/DR & compliance tools: DORA, NIS2, NIST CSF, GDPR, SOC 2, CMMC, CAF, ISO 27001, FCA/PRA.
Nograio.github.nograai/nogra-mcp
Verify-before-done trust layer for AI-assisted work. 32 tools, local-first, no credentials.
mcp-crewd-rsio.github.DioNanos/mcp-crewd-rs
Cell fabric daemon: spawn and coordinate Claude/Codex/pi worker cells over MCP. Audited.
HTTPio.github.Abhishekkumar2021/http
HTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting.
loudcheckio.github.chaoz23/loudcheck
Loudness compliance verdicts (EBU R128, ATSC A/85): pass/fail with exact ffmpeg remediation.
ThinkNEO Control Planeai.thinkneo/control-plane
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.
ZEN SecDBcloud.nttzen.secdb/zen-secdb
ZEN SecDB MCP server for CVE intelligence, CVSS/EPSS scoring, advisories, SSVC, and package audits.
IntakeQ MCPio.github.oktopeak/intakeq-mcp
IntakeQ/PracticeQ MCP connector with HIPAA §164.312(b) audit logging on every PHI read/write
AgentGuard — security checks for AI agentsio.github.shuaicongxiaomai/agentguard
Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
KPN Persona Runtimespace.mysoma/kpn
Verify a persona's DID-signed identity and query value-based judgment — advisory only, no actions.
ActionProofio.github.Burakfenerci5/actionproof
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
TractorBeeam365 MCPio.github.Ringosystems/tractorbeeam-mcp
MCP server for Veeam Backup for Microsoft 365: read-only review + gated, audited restore tier.
Eleion Scannerio.github.hernaninverso/eleion-scanner-mcp
Register/verify your domains, queue security scans, and read findings (CVE, severity).
eleata Claim Verifierio.github.hernaninverso/eleata-verify-mcp
Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).
hushcom.royashbrook/hush
A secret store for AI agents: the agent never sees the plaintext.
mytesla.ioio.mytesla/mytesla
Control your Tesla from your AI assistant - climate, charging, access, and security.
LaunchTrustco.launchtrust/launchtrust
Compliance & security scan for your app: secrets, exposed files, headers, privacy, AI-disclosure.
Trust Gateio.github.CWNApps/trust-gate-mcp
Post-quantum, tamper-evident receipts for agent actions. Ed25519 + ML-DSA-65, offline verify.
Avalara Classificationcom.avalara/classification
Classify, validate & verify HS codes and access tariff compliance data for cross-border trade
Avalara Cross-Bordercom.avalara/cross-border
Cross-border duty-rate and Trade & Tariff content lookups with product compliance and restrictions
URL Safety Validator MCPio.github.OjasKord/url-safety-validator-mcp
AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.
Data Compliance Classifier MCPio.github.OjasKord/data-compliance-mcp
Classify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.
VAT Validator MCPio.github.OjasKord/vat-validator-mcp
Validate EU, UK, AU VAT numbers for AI agents. EU ViDA e-invoicing compliance.
Anaconda MCPio.github.anaconda/anaconda-mcp
Beta conda env/package MCP server; requires conda, auth, and Beta Terms.
OFAC SDN Screeningcom.bonissystems/ofac-sdn-screening
Screen a name against the U.S. Treasury OFAC SDN list. Information, not a compliance determination.
Native Soildev.nativesoil/soil
Save an AI chat's working state, load it in any other model or provider. Verified, secret-safe.
Faroio.github.vedux98/faro
Verify URLs, payees, and messages before acting: red/yellow/green trust verdicts for agents.
Zhiji Signal — Market Phase Detectioncom.run402.zhiji-signal/mcp
A-share HS300 phase signals via Landau-Ginzburg framework. No auth required.
Zhiji Daily Report — Market Briefcom.run402.zhiji-daily-report/zhiji-signal
Daily A-share market brief with LG phase signals. No auth required.
BLOCKTRUST TrustScanio.github.brnbtech770/blocktrust-trustscan
Trust verification for AI agents: identities, domains, phishing, contacts, Trust Circle, Vault.
Free Agent Economy Labapp.replit.austere-unsteady-pdf/free-agent-economy-lab
Free buyer-side outcome verification and provider comparison for supplied agent receipts.
Agent Receiptscom.dropwatchhq/agent-receipts
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Qinisoio.github.qinisolabs/qiniso
Deterministic fact verification for AI agents — checksums & curated data, not guesses.
keywardio.github.arturayupov/keyward
Local encrypted secret broker for AI agents: request keys by name, approve each use over MCP.
Allowance MCPcom.useallowance/allowance-mcp
Secure agent purchasing with human-approved virtual cards, receipts, and audit trails.
JuriBaseio.github.andersongadelhaadv-cmyk/juri-verify
Busca e verifica jurisprudência brasileira real (+400 mil julgados) — anti-alucinação para IA.
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.