Annuaire des serveurs MCP
53,729 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
- 34,042 serveurs distants
- Mis à jour toutes les heures
Elicitly Proai.elicitly/pro
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
VerixID Verifiercom.verixid/verifier
Verify VerixID proof-of-existence records and optionally prove ownership.
Agent Action Gateio.github.AAH20/agent-action-gate
Gate/Prove: deny unattended destructive agent tools. Instant Audit $499 on a2zsoc.com.
MCP Remote Sshgithub.com/faizbawa/mcp-remote-ssh
SSH access with persistent sessions, SFTP and port forwarding, with secrets injected via stdin and redacted from output before reaching the LLM.
MCPLookupcom.mcplookup/mcp
Look up independent trust ratings and security, maintenance, and adoption evidence for MCP servers.
Fullmaktai.fullmakt/fullmakt
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
MCP-Bastionio.github.vaquarkhan/mcp-bastion
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
Twelve Permissionscom.twelvepermissions/twelve-permissions
Browse, verify and buy Twelve Permissions NFTs on XRP Ledger. Every claim is checkable.
SentinelX MCPapp.sentinelx/sentinelx
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
FinCEN (EUA)io.github.mcp-dir/fincen-mcp
Checks whether a name is on the FinCEN (US financial crimes) lists, for compliance and AML due dilig
FBI Most Wantedio.github.mcp-dir/fbi_most_wanted-mcp
Checks whether a name is on the FBI Most Wanted list, for compliance and AML due diligence. Platform
Sanções ONU (Conselho de Segurança)io.github.mcp-dir/sancoes_onu-mcp
Checks whether a name is on the UN Security Council consolidated sanctions list, for compliance and
Sanções Reino Unido (HM Treasury)io.github.mcp-dir/sancoes_reino_unido-mcp
Checks whether a name is on the UK's financial sanctions list (HM Treasury), for compliance and AML
Sanções Suíça (SECO)io.github.mcp-dir/sancoes_suica-mcp
Checks whether a name is on Switzerland's international sanctions list (SECO), for compliance and AM
IBAMA Regularidadeio.github.mcp-dir/ibama_regularidade-mcp
Issues the environmental compliance certificate from IBAMA for a person or company from the CPF or C
Sanções União Europeiaio.github.mcp-dir/sancoes_ue-mcp
Checks whether a name is on the European Union's financial sanctions list, for compliance and AML du
Sanções Canadá (SEMA)io.github.mcp-dir/sancoes_canada-mcp
Checks whether a name is on Canada's international sanctions list (SEMA), for compliance and AML due
Compliance de Apostasio.github.mcp-dir/compliance_apostas-mcp
Checks a person's compliance indicators for the betting sector from the CPF. Platform-hosted, no cre
Beneficiário Finalio.github.mcp-dir/beneficiario_final-mcp
Identifies the ultimate beneficial owner of a company or person from the CNPJ or CPF, for compliance
Sanções Austrália (DFAT)io.github.mcp-dir/sancoes_australia-mcp
Checks whether a name is on Australia's international sanctions list (DFAT), for compliance and AML
OFAC (Sanções EUA)io.github.mcp-dir/ofac-mcp
Checks whether a name is on OFAC (US) sanctions lists, including SDN and Non-SDN, for compliance and
PEP (Pessoa Exposta Politicamente)io.github.mcp-dir/pep-mcp
Checks whether a person is a Politically Exposed Person (PEP) from the CPF, for compliance and AML d
raccha.aiai.raccha/raccha
MCP-first toolbox for agents: KV storage, auth, queue, and utility tools. Free in early access.
Kashifnet.bottletech.kashif/audit
Scores a website's online presence 0-100 and lists the top issues to fix. English/Arabic.
Agoraio.github.mo-grantsmith/agora
Find governed AI capabilities and verify signed receipts. Read-only, no account.
SendGrid Secureio.github.Choppaaahh/sendgrid-mcp-secure
Security-first SendGrid MCP server: dry-run default, recipient allowlists, rate caps, audit log.
ScopeGateio.github.alifanov/scopegate
Permission gateway for AI agents: scoped MCP endpoints over 27 services, audited and revocable.
Ouroborosio.github.Q00/ouroboros
Pins an acceptance spec; the verify command and expected output never enter the success contract.
Hiberdenio.github.Agaveis/hiberden-mcp
Read and verify your local media archive's 3-2-1 coverage across tape, disk, NAS, and cloud.
ComplianceCN — toys, batteries, cosmetics, food contact: CE, GPSR, UN 38.3, CPC/GCC and moreio.github.liamohtee/agentcn
Source-cited EU/UK/US/AU market-access checks for Amazon and cross-border product compliance.
mcp-auditio.github.firatmio/mcp-audit-proxy
Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.
Bibverifyio.github.Hylouis233/bibverify
Verify and repair BibTeX references with DOI-first MCP tools.
Flaredev.flarehq/security
Scan a running app or repo for leaked secrets, exposed routes and open RLS, and verify live keys
DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)com.fronesislabs/dcl-trust-oracle
AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
SMB RFP Copilotcom.checkmycontractorquote/smb-rfp-copilot
Extract RFP requirements, deadlines, compliance items, and response checklist.
WhitePactio.github.Guruprasath-Annadurai/whitepact
AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.
AI Divination Skillsio.github.sapuyou45-bit/ai-divination-skills
Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.
ListingGood MCPio.github.ryanyang828/listinggood
Get recommended by Amazon's AI. Hosted MCP server for Amazon listing compliance & generation.
CR8 Agent Commonsdev.cr8/commons
A public message board for AI agents. Read the feed, post, reply. No auth; identity self-declared.
EnvoiSMSma.envoisms/envoisms
Send SMS/WhatsApp and verify OTP codes in Morocco (+212) and worldwide. Direct carrier routing.
Agent Verification Utilitydev.kgninja.agent-economy/agent-verification-utility
Deterministic JSON checks with signed evidence and x402-paid execution
Hares — MCP security scannerio.github.alialrikabi313/hares
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
LatAm Fintech Synthetic Dataio.github.jmendozapuche/latam-fintech-synthetic-data
Privacy-safe synthetic financial data for LatAm fintech, AI agents, testing and ML.
Fidenta Verifyai.noevant/fidenta-verify
Independent fact-checking for AI answers: a verdict and sources for every claim.
BT Ops MCPio.github.tangchangzhe/bt-ops-mcp-server
Secure MCP server for BT Panel operations with scoped permissions and audited writes.
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.
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.