Annuaire des serveurs MCP
53,711 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
- 34,030 serveurs distants
- Mis à jour toutes les heures
Agent Runtime Proofio.github.fantasyce/agent-runtime-proof
Verify whether a local Agent or MCP runtime matches an approved artifact.
Security Recipesio.github.stevologic/security-recipes
Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.
Brainiall NLPcom.brainiall/nlp
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Atinamos Evidenceuk.co.atinamos/evidence
Read-only verification evidence for paid machine services and buyer policy checks.
Zyphecom.zyphe/zyphe-mcp
Run KYB and AML case reviews and configure Zyphe verification flows, forms and API keys.
Stashbaseio.github.stashbase/mcp
Secrets for developers and agents—secure context and workflows without exposing secret values.
llms.txt Generatorde.llms-txt-generator/llms-txt
Create, validate and audit llms.txt, incl. the Lighthouse Agentic Browsing check.
Sentinel Scanio.github.Ventrova/sentinel-scan-cli
MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.
Vibes-Coded Agent Security and Commerce Toolsio.github.doteyeso-ops/mcp-server-vibes-coded
Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools.
Kadent Scanso.kadent/kadent-scan
Free, read-only security scanner for remote MCP servers, before you connect them.
AccordTraceio.github.Kosta1985/accord-trace
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
DAEMON — on-chain generative art (8004 NONCE + KOINE)io.github.KBD26/daemon-art
Mine, mint and verify 8004 NONCE proof-of-work art on Ethereum L1.
1Claw Vaultio.github.1clawAI/1claw-mcp
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
verifiable-claim-seedio.github.elwsls/verifiable-claim-seed
Zero-dependency verifiable-claims MCP: validate safely, verify with allow_execution, self-test.
verifyfirstio.github.simulacra/verifyfirst
Look up what your verification method cannot see: 48 failures that report success.
Sovereign Gatewayio.github.mattijsmoens/sovereign-mcp-gateway
Gating proxy for MCP servers: policy, verification and one audit trail across upstreams.
Oracleboneio.github.sapuyou45-bit/oraclebone
Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.
Symfony Agent MCPio.github.shakaran/symfony-agent-mcp
Read-only Symfony introspection: routes, services, entities, Doctrine, security, Twig and more.
Easy2257io.github.Agaveis/easy2257-mcp
Read your 18 U.S.C. 2257 compliance records: what is outstanding, expiring, or certified.
NoshUp: Meal Planning & Grocery Budgetio.github.navshainc/noshup
Grocery meal planning, budgets, and flyer deals for Canadian households. Auth required.
Agent Reliabilitydev.agentreliability/agent-reliability
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
ERC-8126 Scanuk.co.cybercentry/erc-8126-scan
378k+ ERC-8004 agents and their security verifications. Two tools free, the rest USDC over x402.
Live Listing Proofdev.workers.mattskowronis.live-listing-proof/verify-listing
Verify a public listing URL and return source-supported facts or explicit fail-closed states.
Supcom.supwire/sup
Read the public Sup wire over hosted MCP, or use local clients to claim, send, and verify receipts.
OneDroid Synapseai.onedroid/synapse
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
Venue Authorityio.github.kingymon1/venue-authority
Verify food-service facilities against supported regulator records.
FreeToolBoxes Agent Toolsio.github.DAMediaCo/agent-tools
Exactly 50 data transformation and live web verification tools for AI agents.
webPostoio.github.mcp-dir/webposto-mcp
webPosto ERP (management for gas stations and convenience stores) via session capture with your auth
Compliance & Sançõesio.github.mcp-dir/compliance-mcp
Due diligence & KYC: PEP, national and international sanctions (OFAC, UN, EU, UK, FBI, INTERPOL, FIN
KnowBe4io.github.wyre-technology/knowbe4-mcp
MCP server for KnowBe4 security awareness training — users, groups, training, phishing campaigns.
MCPComp Diagnosticsdev.mcpcomp/diagnostics
Grade an MCP server's auth against the spec and diagnose which layer a failure is in.
ThreatLockerio.github.wyre-technology/threatlocker-mcp
MCP server for ThreatLocker — zero-trust endpoint protection, allowlisting, and policies.
Colterio.github.mfbahc/colter
Colter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.
Blackpoint Cyberio.github.wyre-technology/blackpoint-mcp
MCP server for Blackpoint Cyber MDR — alerts, threats, and operations.
Securedact MCPio.github.GigantesHJI/securedact-mcp
Local-first privacy MCP server for sensitive AI workflows
obsifyio.github.Formative-Sum41/obsify
Local, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.
Sealgateio.github.Edison-Watch/sealgate-mcp
Sealgate gateway proxy: list governed MCP servers and review agent session and audit status.
MCP stdio ShellGuardio.studiomeyer/stdio-shellguard
Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.
Skowron Compliance Gatewaydev.workers.mattskowronis.skowron-compliance-gateway/compliance
OFAC, LEI, EU VAT, AI Act, and company compliance preflight for agents.
SOC 2 Complianceio.github.CSOAI-ORG/soc2-compliance-ai-mcp
SOC 2 Type II compliance for trust services criteria (security, availability, processing
SEC Filing Proofdev.workers.mattskowronis.sec-filing-proof/verify-sec-filing-claim
Verify whether an official SEC filing supports a specific financial claim.
Source Claim Proofdev.workers.mattskowronis.source-claim-proof/verify-source-claim
Verify whether a supplied public source currently supports one atomic factual claim.
Elucora Evidence APIcom.elucora/evidence
Capture a web source, or seal a hash you hold, into a signed receipt anyone can verify offline.
Hera Agent Unityio.github.NotNull92/hera-agent-unity
Control and verify a live Unity Editor through a local, low-token MCP server.
MCP Servergithub.com/rafapra3008/cervellaswarm/tree/main/packages/mcp-server
Verify agent communication protocols with session types and Lean 4 proofs to catch deadlocks and role violations; includes a linter, formatter and LSP.
Vett Compliance MCP Serverio.github.Gorp405/vett-compliance
Sanctions, PEP, watchlist, recall, business, and contract screening. Free tier, no auth required.
Waqi — AI Privacy Layerio.github.ajprolific/waqi
Redacts PII from your business tools before the AI sees them — with a provable audit log.
Elicitly Proai.elicitly/pro
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
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.