Annuaire des serveurs MCP
54,097 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
- 34,356 serveurs distants
- Mis à jour toutes les heures
io.github.CSOAI-ORG/eu-ai-act-compliance-mcpio.github.CSOAI-ORG/eu-ai-act-compliance-mcp
Eu Ai Act Compliance MCP Server by MEOK AI Labs
io.github.CSOAI-ORG/dora-compliance-mcpio.github.CSOAI-ORG/dora-compliance-mcp
DORA (EU Digital Operational Resilience Act) compliance for AI agents. 5-pillar audit, incident ...
global.rootz.companies/companiesglobal.rootz.companies/companies
Verify a US company: officers, agents, motor carriers. Flags when our status disagrees with state.
com.obeliskgate/trust-toolscom.obeliskgate/trust-tools
Website security ratings, token verification, and tamper-evident ledger heads from Obelisk Gate.
ai.aqta/sealai.aqta/seal
Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
Execute delegatecall-vulnerability-mcpio.github.Evozim/delegatecall-vulnerability-mcp
Premium agentic endpoint for delegatecall-vulnerability-mcp.
Execute darkweb-threat-feed-mcpio.github.Evozim/darkweb-threat-feed-mcp
Premium agentic endpoint for darkweb-threat-feed-mcp.
Execute conflict-minerals-audit-mcpio.github.Evozim/conflict-minerals-audit-mcp
Premium agentic endpoint for conflict-minerals-audit-mcp.
Execute bio-safe-audit-mcpio.github.Evozim/bio-safe-audit-mcp
Premium agentic endpoint for bio-safe-audit-mcp.
Execute bias-auditor-mcpio.github.Evozim/bias-auditor-mcp
Premium agentic endpoint for bias-auditor-mcp.
Execute auth-sentinel-mcpio.github.Evozim/auth-sentinel-mcp
Premium agentic endpoint for auth-sentinel-mcp.
Execute ashrae-compliance-mcpio.github.Evozim/ashrae-compliance-mcp
Premium agentic endpoint for ashrae-compliance-mcp.
Execute ad-fraud-click-detector-mcpio.github.Evozim/ad-fraud-click-detector-mcp
Premium agentic endpoint for ad-fraud-click-detector-mcp.
Execute ad-spend-auditor-mcpio.github.Evozim/ad-spend-auditor-mcp
Premium agentic endpoint for ad-spend-auditor-mcp.
com.vigotime/toolscom.vigotime/tools
Free German workforce calculators (bridge days, net working time, staffing/PeBeM) - no auth needed.
io.github.dasasian/firebase-mcp-serverio.github.dasasian/firebase-mcp-server
MCP server for Firebase — Firestore, Storage, Auth, and Cloud Logging, with schema validation.
io.github.beepboop2025/umbra-proofio.github.beepboop2025/umbra-proof
Verify Umbra bridge accountability proofs (signed receipts, checkpoints, Merkle inclusion).
IMPOCOR-AI Nexusio.github.professoryilmaz1/impocor-ai-nexus
Agent-native security, trust, reliability, data and procurement tools for AI workflows.
com.everlange/mcpcom.everlange/mcp
Everlange: audit AEO on 67 criteria across 10 answer engines, apply fixes, prove the gain.
io.github.arose26/make-audit-mcpio.github.arose26/make-audit-mcp
Audit Make.com blueprints before importing: hardcoded secrets, dangling refs, risky settings.
io.github.arose26/xlsx-audit-mcpio.github.arose26/xlsx-audit-mcp
Audit Excel workbooks: formula dependency tracing, circular references, risk smells. Local only.
io.github.pooriaarab/aigentifyio.github.pooriaarab/aigentify
Audit and generate agent-native product surfaces
io.github.SaravananJaichandar/etchio.github.SaravananJaichandar/etch
Etch is a signed audit chain for AI agent decisions, offline-verifiable against pinned public keys.
io.github.Rinava/umbryn-mcpio.github.Rinava/umbryn-mcp
Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.
io.github.agentready-market/auditio.github.agentready-market/audit
AgentReady.market audit: can an AI shopping agent find, understand and BUY on this store? /100.
io.github.eobi/nemesis-shieldio.github.eobi/nemesis-shield
Positive-security for apps, APIs, LLMs and edge, plus fraud scoring and identity/AML screening.
io.github.CSOAI-ORG/csoaiio.github.CSOAI-ORG/csoai
Signed deterministic AI-governance measurement: EU AI Act cards + agent-callable record verify.
com.pcrzero/mcpcom.pcrzero/mcp
Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.
io.github.Aidress-ai/aidressio.github.Aidress-ai/aidress
Verify, discover, and rate AI agents before transacting.
dev.veritap/veritapdev.veritap/veritap
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
U.CASH Pay (merchant MCP)io.github.uantum/mcp-ucashpay
U.CASH Pay merchant MCP: create checkouts, verify webhooks, read settings. Non-custodial.
io.github.sercanmetalore/ai-act-compliance-mcpio.github.sercanmetalore/ai-act-compliance-mcp
EU AI Act uyum MCP sunucusu — risk sınıflandırma (madde atıflı), rol bazlı yükümlülük listesi…
io.github.RudrenduPaul/truesignalio.github.RudrenduPaul/truesignal
Wraps the truesignal CLI as a single generic MCP tool for threat/connector status checks.
io.github.RudrenduPaul/paceproofio.github.RudrenduPaul/paceproof
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools.
io.github.RudrenduPaul/skillguardio.github.RudrenduPaul/skillguard
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
io.github.mlawsonking/agent-firewall-mcpio.github.mlawsonking/agent-firewall-mcp
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
AgentFabric — Human-in-the-Loop Review & Approvalio.github.enzoduit/agentfabric
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
au.com.aiframework/australian-ai-governance-frameworkau.com.aiframework/australian-ai-governance-framework
Australian AI governance framework mapped to the Privacy Act and sector laws your AI use triggers.
org.govenantstandard/govenant-auditorg.govenantstandard/govenant-audit
Run the GOVENANT trust audit on your own AI agents — read-only, aggregate-only. Detects…
io.github.tunahanaliozturk/partner-center-mcpio.github.tunahanaliozturk/partner-center-mcp
Unofficial Partner Center REST API knowledge & codegen assistant (scenarios, auth, errors).
io.github.smartflowproai-lang/verifyio.github.smartflowproai-lang/verify
Independent x402 observatory on Base. Sealed decomposition + endpoint audits paid over x402 itself.
io.github.helloaigent-dev/helloaigent-subscriberio.github.helloaigent-dev/helloaigent-subscriber
Subscribe your agent to Hello Aigent feeds: discover, fetch signed updates, verify, and act.
Occludra — MCP Gateway (AI Security Gateway)ai.occludra/mcp-gateway
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
io.github.getaegis/aegisio.github.getaegis/aegis
Credential isolation for AI agents. Inject secrets at the network boundary.
io.github.vpatser1/mcp-server-security-scannerio.github.vpatser1/mcp-server-security-scanner
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
io.github.KryptosAI/mcp-seatbeltio.github.KryptosAI/mcp-seatbelt
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
com.threadlinqs/intelthreadlinqs-mcpcom.threadlinqs/intelthreadlinqs-mcp
Threadlinqs threat-intelligence MCP — 73 tools: threats, detections, IOCs, actors, C2, MITRE, CVEs
com.hirosecure/agentscom.hirosecure/agents
Programmatic control of the Hiro security platform: scans, tasks, plans, and approvals.
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.