Annuaire des serveurs MCP
53,774 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
- 34,087 serveurs distants
- Mis à jour toutes les heures
Intent-Verified Development (IVD)io.github.leocelis/ivd
33 tools that make AI write, implement, and verify intent against explicit, testable constraints.
AI2Humanio.github.richard7463/ai2human-mcp
Dispatch human-execution tasks with proof verification, local checks, and compliance reviews.
AgentPub — Public Chat for AI Agentsio.github.liboy119/agentpub
Public, agent-native chat for AI agents. 6 channels. Zero auth. MCP + A2A + WebSocket.
ContextOverfloworg.contextoverflow/library
Describe what's going wrong with your AI; get the named technique both of you can read. No auth.
Molpha MCPio.github.molpha/mcp
MCP server that lets AI agents create, fetch, verify, and publish Molpha oracle data.
klanexio.github.chrassy/klanex
Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
VMware NSX Securityio.github.zw008/vmware-nsx-security
VMware NSX security: DFW policies, security groups, tags, Traceflow, IDPS — 21 MCP tools.
VMware Hardenio.github.zw008/vmware-harden
VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection.
Stellaroid Earnio.github.Iron-Mark/stellaroid-earn
Read-only MCP server: verify credentials and browse escrows on the Stellar testnet contract.
Netallion MCP Liteio.github.netallion/netallion-mcp-lite
Local secret & credential checks for AI-assisted dev — runs on your machine, results redacted.
QuoteFirstai.quotefirst/quotefirst
Get dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.
Agentic Diaries Auditio.github.kandikandikandi/behavioral-audit
Checks what a support agent knew but did not say against its policies. Free tier, no login.
Security Intel MCPio.github.selflabbs/security-intel-mcp
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
andonio.github.gulmezeren2-byte/andon
Deterministic verification for AI-generated analysis: run a spec, inspect or diff a workbook
Black Duck Security Scannercom.blackduck/mcp-server
AI-powered security scanning using Black Duck Signal for vulnerability detection.
Phishuntio.github.0xDanielLopez/phishunt
Public phishing feed: suspicious/confirmed phishing URLs detected hourly. No auth, CC0.
DOS — the trust substrate for agent fleetsio.github.anthony-chaudhary/dos-kernel
Verify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.
IdentArk Gatewayio.identark/gateway
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Trusteedio.github.trusteed-io/trusteed-mcp
CTEM for your Trusteed tenant: security summary, findings, compliance gaps, and scans via OAuth.
Decision Logai.decisionlog/mcp
Append-only decisions with provenance, supersession, retrieval, and audited MCP actions.
State of Web Vitalsio.github.corewebvitals/state-of-cwv
Core Web Vitals metrics by CMS, CDN, and framework — free remote MCP, no auth.
Niroio.github.apxlabs-ai/niro
AI pentester for PRs — finds exploitable bugs and hands your developer agent the fix.
Toolcallclick.toolcall/toolcall
30 pay-per-call APIs for AI agents: compliance, trade, safety, web, data. USDC on Base via x402.
CyberHuaTuoio.github.JinNing6/cyberhuatuo
Gold-first AI-agent traceback diagnosis, exact fixes, verification, and reusable prescriptions.
TMCPio.github.jakyeamos/tmcp
Composable skill packets, harvests, workflow routing, and release/audit rubrics over MCP.
Signal Oracleio.github.NeruoticFarrow/signal-oracle
Pay-per-call change-intelligence feeds for AI agents over x402 (deps, security, regs, tariffs)
Scanndcom.scannd/scannd
Trigger security scans and read reports/vulnerabilities via the hosted Scannd API. Free: 2 scans/mo.
eurc402 — EU compliance (VAT + company data)com.eurc402/eu-compliance
Free EU VAT (VIES) + pan-EU company data (10 registers), payable in EURC/USDC via x402.
Positifai.positif/positif
The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger.
Scout Securityio.github.Varpost/scout
Deterministic, zero-token security scanner your AI agent calls to find and re-verify issues.
kcp-harness — KCP compliance proxyno.cantara/kcp-harness
MCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.
Thor Henning Hetland — signed knowledge weborg.totto/knowledge
Thor Henning Hetland's signed knowledge web: plan, load and verify ed25519-signed KCP units.
HODLXXI Read-Onlyio.github.hodlxxi/hodlxxi-readonly
Public read-only MCP server for HODLXXI agent identity, trust, receipts, and verification.
Physical Capability Cloudnetwork.capability/physical-capability-cloud
Discover, hire, and verify real-world physical capability through MCP.
Human For AIdev.humanforai/humanforai
Hire a real human for real-world verification, product testing, AI output review, and errands.
Ansvar: Threat Intelligenceeu.ansvar/threat-intel
CVE intelligence, STRIDE, OWASP test cases via Ansvar Gateway. Cited, OAuth + paid.
Works With Agents MCPio.github.vystartasv/wwa-mcp
14 MCP tools: facts, pitfalls, skills, handoff protocols, trust scores, identity verification.
B20 Checkcom.b20check/b20check
Verify B20 tokens on Base: issuer powers, imposter detection, signed EIP-712 verdicts.
Acta — Verifiable Agent Memoryio.github.Kylewilson04/acta-mcp
Verifiable agent memory with signed ledger receipts — verify every write offline.
Tailscale RMCPai.dinglebear/tailscale-rmcp
Rust MCP server and CLI for Tailscale devices, users, keys, policies, and auth.
Meta Councilcom.meta-council/decision-intelligence
Multi-expert decision intelligence with transparent synthesis and auditable workflows.
Valtaio.github.Billionaire664/valta-mcp
Financial governance for AI agents — spend gates and audit trail exposed as MCP tools.
mcp-scanio.github.CodingSelim/mcp-scan
Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.
MadTacodev.madtaco/mcp
Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.
Defiance Storefrontio.defianceinternational/storefront
Read-only catalog, sequence, evidence, policy, and COA-verification lookup for an RUO supplier.
MCP Shieldgithub.com/rob925/mcp-shield
Static security scanner for MCP servers and agent tools: detects secrets, shell execution, risky tool descriptions, environment access and prompt injection.
Touchstonecv.touchstone/touchstone
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Fabler x402 Toolscom.fablerlabs/x402-tools
Free catalog and 2,048-character secret-scan preview for Fabler's x402 agent tools on Base.
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.