English Français العربية

Annuaire des serveurs MCP

53,059 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
  • 33,564 serveurs distants
  • Mis à jour toutes les heures

2,103 serveurs

Alienvault Otxio.github.pipeworx-io/alienvault-otx AlienVault OTX MCP — Open Threat Exchange (free with key) Distant oct. 2026 Airqualityio.github.pipeworx-io/airquality Air Quality MCP — wraps air-quality-api.open-meteo.com (free, no auth) Distant oct. 2026 Airportsio.github.pipeworx-io/airports Airports MCP — wraps AirportGap API (free, no auth required), plus a D1 copy of the OurAirports… Distant oct. 2026 Agifyio.github.pipeworx-io/agify Agify MCP — age prediction from first name (agify.io, free, no auth) Distant oct. 2026 Adviceio.github.pipeworx-io/advice Advice MCP — wraps Advice Slip API (free, no auth) Distant oct. 2026 Pre-install canonical-identity verificationcom.textforagents/pre-install-canonical-identity-verification Pre-install canonical-identity verification for MCP servers and skills, with signed verdicts. Distant oct. 2026 GuildControl MCPapp.lasers.guildcontrol/discord Safety-first MCP server for Discord with privacy-safe reads, audits, and reviewed administration npmocimcpb oct. 2026 ClevSec EU compliance toolsone.clevsec/eu-compliance Deterministic, sourced EU compliance checks: NIS2, DORA, GDPR and the Cyber Resilience Act. Distant oct. 2026 CrowdStrike Falcon MCP Serverio.github.CrowdStrike/falcon-mcp Connects AI agents with CrowdStrike Falcon for security analysis and automation. pypi oct. 2026 Default Privacyio.github.privatebydefault/default-privacy Sourced privacy answers: how private an app is, tool picks, app swaps, de-Googling, breaches. Distant oct. 2026 AcidPeakcom.acidpeak/acidpeak Read-only vulnerability intelligence: CVEs, exploitation evidence, fixes and product matches. Distant oct. 2026 FaxSealio.github.grichardomi/faxseal Send, receive, and verify faxes from AI assistants and agents via FaxSeal. Distant npm oct. 2026 Teramindio.github.WYRE-AI/teramind-mcp MCP server for Teramind's insider-threat/employee-monitoring API (read-only, metadata-only surface). oci oct. 2026 ESET PROTECTio.github.WYRE-AI/eset-protect-mcp MCP server for ESET PROTECT's ESET Connect API - device, EDR, vulnerability, patch, and user data. oci oct. 2026 APSA mobile app security auditio.github.ictechgy/apsa Local, evidence-graded Android/iOS security audits of source, APK, AAB and IPA for AI agents. pypi oct. 2026 MCP ZAP Serverio.github.dtkmn/mcp-zap-server Safe, self-hosted ZAP operator for guided AI security scans and reports. oci oct. 2026 Johto Datacom.johtodata/johto-data Johto Data: pay-per-call company, compliance and filings data via x402. Free sample on every tool. Distant oct. 2026 ShipLatchcom.shiplatch/scanner Free passive security scan for AI-built apps: leaked API keys, public .env files, security headers Distant oct. 2026 Data Prismio.github.AindriuB/data-prism Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients. oci oct. 2026 MCP OAuth remediation verificationcom.textforagents/mcp-oauth-remediation-verification Three-leg MCP OAuth remediation verdicts, proven behaviourally against a canary server. Distant oct. 2026 AgentRaaS wrapio.github.agentraas/agentraas Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged. pypi oct. 2026 BailingHub for Business Operationsio.github.bailinghub/bailinghub-governance Let AI agents query and operate business systems with authorization, approval and audit trails. npm oct. 2026 Aurelmarkio.github.Ishan73744/aurelmark EU compliance facts with sources: TED tender deadline changes, CBAM values, EU deadlines, EUDR scope Distant oct. 2026 MCP Dandangithub.com/82ch/MCP-Dandan Real-time security framework for MCP servers that detects and blocks malicious agent behavior by analyzing tool call patterns and intent. Communauté oct. 2026 Outcome-verified watchdog for scheduled agentscom.textforagents/scheduled-agent-outcome-verification Watchdog that verifies scheduled agents' artifacts itself — never the claim. Distant oct. 2026 Intent Cloak: query-intent privacy for agentscom.textforagents/intent-cloak-query-privacy Query-intent privacy for agents: threshold cloaking with signed exposure receipts. Distant oct. 2026 ExchangeRebel — pay-per-call APIs for AI agents (x402 on Solana)com.exchangerebel/exchangerebel 166 pay-per-call APIs for AI agents: market, company, dev + verification tools — x402 on Solana. Distant oct. 2026 Rubrik Security Cloudio.github.rubrikinc/rubrik-mcp Connect AI assistants to the Rubrik Security Cloud GraphQL API to discover, query, and automate. pypi oct. 2026 Pre-open repo agent-surface auditcom.textforagents/repo-agent-surface-pre-open-audit Per-harness pre-open verdict on a received repo's agent-control surface. Distant oct. 2026 YesTechie — UniFi Network & Security Integratorcom.yestechie/site UniFi quotes, case studies and network, camera, access config guides from a nationwide integrator. Distant oct. 2026 Synthex Forge — x402 Paid Agent Servicescom.synthexforge.x402/paid-agent-services Paid agent services settled in USDC on Base via x402. Signed, verifiable, and free to verify. Distant oct. 2026 Evidence-granularity auditcom.textforagents/evidence-granularity-audit Per-claim evidence-granularity verdicts for agent listings, before you transact. Distant oct. 2026 x402 Security & Alpha Oracleio.github.ak10082247-max/x402-sniper-bot Read-only pre-trade honeypot simulation and DEX alpha oracle for Solana and Base. npm oct. 2026 Clawguard MCPgithub.com/joergmichno/clawguard-mcp Security scanner for AI agents that detects prompt injections using regex patterns. Communauté oct. 2026 well-011-sharescandev.workers.rainmaker-wells.well-011-sharescan/sharescan Pre-share scan of text for your terms and secrets/PII. x402 $0.005 USDC, Base. As is, no warranty. Distant oct. 2026 CertScore.ai MCP Lightai.certscore/mcp-light Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS. Distant oct. 2026 Cancellation-outcome verificationcom.textforagents/cancellation-outcome-verification You cancelled the run — did the work actually stop? Distant oct. 2026 Authclick.myinfrastructure/auth Usuários, sessões, logins sociais e webhooks da sua aplicação Distant oct. 2026 Markdev.tatastu/proof Mark: stamp files with a signed, timestamped provenance record. Hash locally; verify free. Distant oct. 2026 Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewalldev.agentdiet/mcp-security Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents. Distant oct. 2026 AgentDiet Real-Time Open-Source Package CVE & GHSA Vulnerability Scanner (OSV.dev)dev.agentdiet/cve-intel Queries live Google OSV.dev vulnerability intelligence for any PyPI, npm, Go, or Rust crate and r. Distant oct. 2026 mcp-gatehouseio.github.nickgeorgeseo/gatehouse Permission tiers, approval gates, and audit logging for MCP servers - the server is the gatekeeper pypi oct. 2026 VerifyLiteio.github.SecondShotAI/verifylite Pay-per-call website safety and URL checks for AI agents. USDC on Base via x402, no API keys. Distant oct. 2026 Maven MCPgithub.com/kirich1409/maven-mcp MCP server / agent plugin for Maven and Gradle dependency intelligence: latest versions, outdated deps, CVEs, changelogs, licenses and project audits. Communauté oct. 2026 SanAlertio.github.plrojek/sanalert-mcp Unofficial threat level from the air for a place in Poland, worked out on your own computer. pypi oct. 2026 Portunusio.github.mdostal/portunus Secret broker for agents: reference secrets by name; values injected only at the execution boundary. oci oct. 2026 mitracore — trust layer for agent worklat.rta/mitracore Verify the artifact, meter the cost, enforce the mandate — one call. Distant oct. 2026 skilllint — vet an agent skill before you install itlat.rta/skilllint Vet an agent skill before you install it: structure, triggers, secrets. Distant oct. 2026

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 27 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.