Annuaire des serveurs MCP
53,596 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
- 33,938 serveurs distants
- Mis à jour toutes les heures
AI-Cost-CLIio.github.ufhouck/aicost-cli
AI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio.
Contendeoapp.contendeo/contendeo
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
VEO 3.1io.github.u2n4/veo-mcp-server
4K video generation via Google VEO 3.1: text-to-video, image-to-video, video extension
Live Audio Intelligenceio.github.ykshah1309/live-audio-intelligence-mcp
Live webcast transcription + vocal stress analysis (F0 jitter, hesitation) for earnings calls.
FramesCLIio.github.wraelen/framescli
Make videos AI-readable. Extract timestamped frames and transcripts from any video for AI agents.
DECIMER MCP Serverio.github.DocMinus/decimer-mcp-server
MCP server for DECIMER image-to-SMILES chemical structure recognition
captcha.cc Human Verificationcc.captcha/captchacc
Human verification CAPTCHA with visual and selective-listening audio challenges.
Image Generator APIio.github.Br0ski777/image-generator
AI image generation from text prompts via Gemini. x402 micropayment.
HTML to Figma — Design Systemio.github.miapre/html-to-figma-design-system
Translate HTML prototypes into Figma using your design system's real components and tokens.
Freebeat MCPio.github.freebeatfit/freebeat-mcp
Freebeat MCP server for AI music videos, effects, and media uploads.
Visuals MCPio.github.harrybin/visuals-mcp
MCP server for interactive visualizations: tables, images, trees, lists, master-detail
AI Vision MCPgithub.com/tan-yong-sheng/ai-vision-mcp
Image, video and object-detection analysis with Google Gemini and Vertex AI for UI/UX evaluation, visual regression testing and interface understanding.
VEED AI Video Generatorio.veed/fabric-mcp
Generate AI talking-head videos with custom characters and voices.
eKYC Suiteio.github.wefi-ai/ekyc-suite
KYC / eKYC MCP server for face compare, liveness, OCR, and image labeling.
deAPI MCP Serverio.github.deapi-ai/mcp-server-deapi
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
AllGoodInspcom.allgoodinsp/mcp-server
Curated design references for AI — real CSS values, typography specs, and color palettes.
Furniture Designerio.github.LuisEnVilla/furniture-designer-mcp
Professional furniture design: specs, validation, cut optimization, BOM, and 3D reports.
MCP Imagenateio.github.mimo-3/mcp-imagenate
MCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)
Speech Shgithub.com/j3k0/speech.sh
Let the agent speak out loud and notify you with a quick summary when it finishes working.
Media MCPgithub.com/Adityaaery20/media-mcp
Local image and video processing: resize, convert, compress, crop, thumbnails, metadata extraction, rotate, flip, filters and ffmpeg-based video operations.
Filtrix AI MCPai.filtrix.mcp/filtrix-ai
Filtrix MCP for image/video generation. Portal: https://agent.filtrix.ai/
xpay Media Studioio.github.xpaysh/media
25+ AI media tools. FLUX, Ideogram, Recraft, Stability AI, MiniMax video, Kokoro TTS.
Keynote MCPgithub.com/ByAxe/keynote-mcp
Control Apple Keynote via AppleScript: create, edit and export presentations, including slides, content, layout and Unsplash images.
Voice Transcriber MCP Serverio.github.fgasparetto/voice-transcriber-mcp
MCP server for transcribing Google Chat voice messages using Groq Whisper API
Brainiall MCP Servergithub.com/fasuizu-br/brainiall-mcp-server
Speech tools: pronunciation assessment with phoneme-level feedback, speech-to-text with language detection and text-to-speech with multiple voices.
Korean Data MCPgithub.com/leadbrain/korean-data-mcp
Real-time Korean web data via Apify: Naver place reviews and news, Melon music chart, Daangn and Bunjang listings and Musinsa fashion rankings.
Smasher Studio — AI Fashion Designio.github.Atenkai/smasher-studio
AI fashion design — product photos, videos, tech packs, colorways & fabric sims.
NOAA GOES Satellite Imagery MCP Serverio.github.mansurjisan/goes-mcp
GOES-18/19 satellite imagery — visible, infrared, water vapor, and composites via NOAA
Image Tools - Background Removal, Upscaling & Face Restorationio.github.fasuizu-br/image-tools
Background removal, 4x upscaling, and face restoration via GPU
Speech AI - Pronunciation, STT & TTSio.github.fasuizu-br/speech-ai
Pronunciation scoring, speech-to-text, and text-to-speech for language learning
SlideMasterio.github.Headdao/slidemaster-mcp
Create AI presentation videos with slides, narration, TTS audio, and MP4 export from any topic.
xSkill AIio.github.hexiaochun/xskill-ai
AI content generation with 50+ models: image, video, TTS, voice cloning, and more.
OGForge MCPio.github.dpozimski/ogforge-mcp
Generate Open Graph images with themes and Lucide icons
Atsuraegithub.com/1000ri-jp/atsurae
Video editing: timeline editing, five-layer compositing, semantic operations and FFmpeg rendering to 1080p H.264.
Comfy Pilotgithub.com/ConstantineB6/comfy-pilot
View, edit and run ComfyUI node-based image generation workflows, with an embedded terminal.
Topaz MCPgithub.com/TopazLabs/topaz-mcp
AI image enhancement (upscaling, denoising, sharpening) via the Topaz Labs API, with models such as Standard V2, Wonder 2, Bloom and Recover 3.
MCP Bench Routerio.github.K1ta141k/mcp-bench-router
Routes design tasks to designarena.ai's top-ranked model via OpenRouter across 14 categories.
OpenAI Tools MCP Serverai.com.mcp/openai-tools
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Lenny Rachitsky Podcast Transcripts MCP Serverai.com.mcp/lenny-rachitsky-podcast
MCP server for structured access to Lenny Rachitsky podcast transcripts. For content creators.
Figma MCP Serverio.github.oabolade/figma_mcp_server_actor
MCP server enabling AI assistants to interact with Figma designs via natural language commands
JustCall MCP Serverhost.justcall.mcp/justcall-mcp-server
JustCall MCP Server enables LLMs and AI agents to make voice calls and send SMS via JustCall APIs.
Sonos Ts MCPgithub.com/Tommertom/sonos-ts-mcp
Sonos control via UPnP: device discovery, multi-room playback, queues, music library browsing, alarms, event subscriptions and EQ settings.
Imagiciangithub.com/flowy11/imagician
A MCP server for comprehensive image editing operations including resizing, format conversion, cropping, compression, and more based on sharp.
Runway AI Video Generationio.github.sidart10/runway-mcp-server
AI video generation with Gen-4, Veo 3, and Aleph editing. Text-to-video, image-to-video, 4K upscale
Callcenter Js MCPgithub.com/gerkensm/callcenter.js-mcp
Make phone calls using VoIP/SIP and OpenAI's Realtime API, and observe the transcript.
Remote Cameramoda.ai/remote-camera
Capture photos remotely from mobile devices via S3-backed upload URLs
Figma MCP Servercom.figma.mcp/mcp
The Figma MCP server brings Figma design context directly into your AI workflow.
MCP Server Nano Bananagithub.com/nanana-app/mcp-server-nano-banana
Image generation with Google Gemini's Nano Banana model.
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.