Annuaire des serveurs MCP
53,744 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
- 34,060 serveurs distants
- Mis à jour toutes les heures
Axiom — Advanced Mathio.github.tufantunc/axiom-math
Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas
MiniURLio.github.addychang/miniurl
OAuth 2.1 short-link tools for AI agents with scoped tokens, approvals, audit logs, and revocation.
capital.new mandate draft toolsnew.capital/mandate-tools
Verify Capital Authority Mandate drafts (SHA-256 replay) + v0 schema. Ceremonies stay human.
FrankKiapp.frankki/letters
The agentic layer of letters. Agents send real printed mail worldwide, German compliance built in.
BlackDome Threat Intelio.github.blackdome-ai/blackdome-mcp
Live honeypot threat intel: attacker IPs, IOCs, credentials, payloads, actors.
Zyrax Guardio.github.tiagosilva07/zyrax-guard
Audit AI agent configs for prompt injection & rogue MCP servers; vet packages
Kavalio.github.LufeMC/kaval
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Arketoai.arketo/arketo
Draw your app's architecture on a live canvas and flag the bottlenecks and security gaps.
Lobuio.github.lobu-ai/lobu
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Nummeropslagio.github.andrey-tut/nummeropslag
Privacy-first Danish caller ID, CVR company lookup, operator data, and community spam signals.
Virohana Businesscom.virohanalife/virohana-business
Virohana business catalogue, pricing, company info & quote intake. Bearer auth, rate-limited.
Tuurio IDio.github.Tuurio/tuurio-id
Manage users, OIDC clients, roles, settings, and audits with tenant-bound OAuth.
CrazySEOio.github.d08m/crazyseo
Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys.
CrazySEOio.github.bolidee/crazyseo
Audit whether ChatGPT, Gemini and Perplexity recommend a site. Readiness checks need no keys.
MCP Customsio.github.mcpcustoms/mcp-customs
Inspect an MCP server for common security risks before you install it. Offline, zero telemetry.
Lians Agent Memoryio.github.ebeirne/lians
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
Warrantio.github.s0fractal/warrant
Record an agent's decisions with reasons anyone can re-execute offline — verify recomputes them.
Taplidio.github.taplid/taplid
Audit AI responses and artifacts with ALLOW, REVIEW, or BLOCK decisions and trust scores.
droplinkedcom.droplinked.mcp/server
Agentic commerce + trust MCP: discover, verify, and transact across droplinked's merchant network.
FabTally Guardio.github.zvmzaretsky/fabtally-guard
Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.
Framekeep Public Discoverycom.framekeep/public
Read-only discovery of Framekeep capabilities, security boundaries, and public resources.
Agentic Mermaidio.github.adewale/agentic-mermaid
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
Scrub MCPcom.malgorath.scrub-mcp/scrub-mcp
Stateless PII redaction over MCP/REST. Free ≤1000 words or $0.01/call; file upload supported.
Knotrik — AppSheet Intelligencecom.knotrik/knotrik
Query and audit AppSheet apps in natural language via Knotrik's pre-scanned definitions.
CalvingWatch Public Knowledgecom.calvingwatch/public-knowledge
Read-only CalvingWatch product, tester, camera, privacy and safety facts; no customer data.
AxioRank: Zero-Trust for AI Agentscom.axiorank/axiorank
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
GIA — Governed Intelligence Architectureio.github.knowledgepa3/gia-mcp-server
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Vahtianio.github.heidihelena/vahtian
Freeze a corpus, check it for drift, keep a hash-chained audit ledger. Local-first, stdlib-only.
SPARDAio.github.zyx77550/sparda-mcp
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
Aevum Securitysg.com.aevumsecurity/agent-surface
Browse Aevum Security's Singapore cybersecurity services and submit a business enquiry.
TAG IT Verifynetwork.tagit/nfc-verify
Verify on-chain lifecycle state and provenance of NFC-tagged physical products.
Ara — audits d'accessibilité RGAAio.github.DavidPivert/ara-rgaa-mcp
Piloter des audits RGAA 4.1 sur Ara, référentiel embarqué. Non officiel.
Bravos AIcom.bravos-ai/bravos
Manage your AI chatbot from your AI assistant: analyze conversations, audit content, configure it.
Wafergraph MCPcom.wafergraph/wafergraph-mcp
Read-only MCP server for wafergraph.com's semiconductor & AI supply-chain data: 30 tools, no auth.
Gentkeycom.gentkey/mcp
One MCP URL for all your connectors — scoped writes, enforced constraints, and a full audit trail.
RTK Motion — Motion Capture, Biomechanics, Threat & Fleet Intelligenceio.rtkmotion/data
Mocap, rehab biomechanics, threat intel, fleet vision. 21 MCP tools, 10 free. x402/USDC paid.
TrustAgent — counterparty verificationio.trust-agent/trustagent-mcp
Is this address safe to pay? OFAC sanctions, ERC-8004 reputation, contract analysis.
Truss Threat Intelligencecom.truss-security/truss-mcp
Query Truss threat intelligence via hosted MCP (OAuth). Growth+ plans.
Prompt Compassio.github.rishabhmpc/prompt-compass
Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.
Regex Safety Auditio.github.tylerscomic-lab/regex-safety-audit-mcp
Detects catastrophic-backtracking (ReDoS) regex risk via AST parsing, with JS-safe rewrites.
MCP Schema Auditio.github.tylerscomic-lab/mcp-schema-audit-mcp
Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.
Actenon Kernelio.github.Actenon/kernel
Verify consequential AI actions before they execute.
TAPtech.human/tap
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
Credda Trustio.github.Credda-io/credda-trust
Check a counterparty's verifiable Credda trust record; verify or present signed credentials.
Mind the Gates — UK level crossingsuk.mindthegates/crossings
Live barrier status and closure forecasts for ~1,600 UK level crossings. Public data, no auth.
ARVI Wine Catalogch.arvi/catalog
Swiss merchant ARVI SA: 27,000+ fine & rare wine labels, 300,000+ bottles ready to ship. No auth.
TAR Engineio.github.qingxuantang/tar-engine
Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.
Intent-Verified Development (IVD)io.github.leocelis/ivd
33 tools that make AI write, implement, and verify intent against explicit, testable constraints.
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.