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
io.github.Cipher208/ariel-memoryio.github.Cipher208/ariel-memory
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
io.github.Vorim-AI-Labs/vorim-mcp-serverio.github.Vorim-AI-Labs/vorim-mcp-server
AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI
com.phronesisintel/phronesis-hermescom.phronesisintel/phronesis-hermes
Decision-assurance for AI agents: an auditable action boundary + receipt before it acts.
io.github.Lokeshwaranramu/quantasealio.github.Lokeshwaranramu/quantaseal
Quantum-safe vault, encryption & compliance for AI agents. NIST FIPS 203/204 ML-KEM-768 + ML-DSA-65.
io.github.groundlogic-ai-source/accessibility-aiio.github.groundlogic-ai-source/accessibility-ai
Scan URLs for WCAG 2.1 violations, generate AI fixes, and produce VPAT 2.5 compliance reports.
ai.marchward/mcp-serverai.marchward/mcp-server
Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
com.websitelaunches/launch-record-lookupcom.websitelaunches/launch-record-lookup
Look up a domain's public Website Launches launch record, owner verification & trust context.
io.github.Baneado98/ci-sentinelio.github.Baneado98/ci-sentinel
Multi-CI security scanner with a live threat-intel feed of compromised CI components
dev.turva/turva-mcpdev.turva/turva-mcp
Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.
tools.knurl/secret-scannertools.knurl/secret-scanner
Scan configs, files, or text for leaked secrets and obvious misconfigurations. Nothing stored.
io.github.AIWerk/mcp-server-vaultio.github.AIWerk/mcp-server-vault
Bitwarden/Vaultwarden for agents: list tagged items, TOTP codes, one-time Sends, save new secrets.
services.gera/mcp-gera-complianceservices.gera/mcp-gera-compliance
Classify AI systems under the EU AI Act and look up obligations and articles. Offline, no auth.
services.gera/mcp-gera-verifyservices.gera/mcp-gera-verify
Verify UK businesses (FSA/CQC) + signed attestations, mandates & receipts for AI agents.
io.github.beneb89/changegamerio.github.beneb89/changegamer
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
io.github.bolyra/shieldio.github.bolyra/shield
Stdio MCP auth proxy: wrap any MCP server with per-tool permission enforcement.
io.github.bolyra/mcpio.github.bolyra/mcp
MCP auth middleware: gate tool calls so only authorized agents can act.
io.github.bolyra/gatewayio.github.bolyra/gateway
MCP auth gateway: verify agent identity, enforce per-tool permissions, block replays, emit receipts.
network.flint/agent-transaction-controlnetwork.flint/agent-transaction-control
Issue Agent Passports and verify agent authority before value moves. Signed verification records.
io.github.LeassTaTT/servicenow-mcp-aiio.github.LeassTaTT/servicenow-mcp-ai
ServiceNow MCP server — 67 tools over the full REST surface, every auth method, flows, diagrams.
io.github.codespar/mcp-redeio.github.codespar/mcp-rede
MCP server for Rede — Itaú-owned BR acquirer: authorize/capture/refund, zero-auth, card tokens
io.github.codespar/mcp-personaio.github.codespar/mcp-persona
MCP server for Persona — developer-first identity verification + KYC (inquiries, accounts, reports)
io.github.codespar/mcp-siftio.github.codespar/mcp-sift
MCP server for Sift — global ML fraud detection: real-time risk scoring, decisions, event ingestion
com.dropwatchhq/compliance-evidencecom.dropwatchhq/compliance-evidence
Dated, signed compliance-evidence packs: gov-fact-grounded claims + exclusion screens + trap-facts.
io.github.spektre-labs/sigma-gateio.github.spektre-labs/sigma-gate
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
io.github.Gareth1953/agent-services-mcpio.github.Gareth1953/agent-services-mcp
MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.
io.github.fpetitit/mcpcheckupio.github.fpetitit/mcpcheckup
Scans remote MCP servers for protocol, security, and TLS issues; exposes scan tools via MCP.
io.github.disclose/lookup-disclose-ioio.github.disclose/lookup-disclose-io
Find the right security-disclosure contact for any internet asset (domain, IP, package, repo, app).
it.elsas/security-intelit.elsas/security-intel
Daily Ed25519-signed security intelligence for AI-agent stacks; CVEs & advisories, paid via x402.
io.github.cmdenney/logicnodes-mcpio.github.cmdenney/logicnodes-mcp
Remote MCP for LogicNodes: Signed PII-Shield flagship + payable x402 agent tools on Base.
io.github.cmdenney/logicnodes-mcp-bridgeio.github.cmdenney/logicnodes-mcp-bridge
Signed PII-Shield: redact PII to an EIP-191 attestation, plus x402 pay-per-call agent tools.
com.getvaletparking/valet-parking-directorycom.getvaletparking/valet-parking-directory
MCP server for valet parking: 789 US operators across 31,186 cities. 7 tools. No auth.
com.seanwinslow/intent-engineeringcom.seanwinslow/intent-engineering
Audit, scaffold, and triage agent intent specs against a 9-section template.
io.github.Kjopstad-IT/rqwstrio.github.Kjopstad-IT/rqwstr
AI-native HTTP security testing MCP server — 17 tools with raw HTTP/1.1 + HTTP/2 control
Security Mcpio.github.varvararatta/security_mcp
MCP server for Security
io.github.ANHQ280/myinvois-mcpio.github.ANHQ280/myinvois-mcp
Malaysian LHDN e-invoicing (MyInvois) compliance rules: scope, validation, change-diffs.
io.github.geraservicesuk/mcp-geraguardio.github.geraservicesuk/mcp-geraguard
Privacy protection: scans, tracker detection, data broker opt-outs.
io.github.geraservicesuk/mcp-geracomplianceio.github.geraservicesuk/mcp-geracompliance
EU AI Act and GDPR compliance: checks, audits, generate policies.
com.obsmetrics.paygent/agentscom.obsmetrics.paygent/agents
Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.
io.github.urbanmorph/irrationalio.github.urbanmorph/irrational
Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI.
io.github.dulzuradev/liveauth-mcpio.github.dulzuradev/liveauth-mcp
MCP server for LiveAuth: PoW + Lightning auth, L402 bundles, and paid MCP tool receipts.
io.github.samarthanalytics-sj/samarth-gtm-mcpio.github.samarthanalytics-sj/samarth-gtm-mcp
Google Tag Manager + read-only GA4 MCP server. Read-only by default, gated writes, audits.
io.github.Kevthetech143/chain-signerio.github.Kevthetech143/chain-signer
Security suite for AI agents: flag drains, permit-phishing & risky actions before signing.
ai.responsibleailabs/rail-scoreai.responsibleailabs/rail-score
Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
io.github.llmops-pro/nostr-ops-mcpio.github.llmops-pro/nostr-ops-mcp
Nostr publishing, queries, and DMs for AI agents, with allowlists, rate limits, and an audit log.
io.github.Kisyntra/agent-sudo-mcpio.github.Kisyntra/agent-sudo-mcp
MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.
CAST Gatekeeper MCP Serverio.github.CAST-Extend/gatekeeper-mcp-server
CAST Dashboard MCP server for compliance, quality, and technical debt insights for AI agents
io.github.Delego-Dev/delegoio.github.Delego-Dev/delego
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
com.verisgov.api/data-accesscom.verisgov.api/data-access
Verified federal funding intelligence with sealed provenance; verify any figure at no charge.
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.