Annuaire des serveurs MCP
52,644 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
- 33,339 serveurs distants
- Mis à jour toutes les heures
Clipformio.github.Clipform/mcp-server
Interactive video forms that capture authentic responses. Build engaging forms in minutes.
Ocireg MCPgithub.com/StacklokLabs/ocireg-mcp
Interact with OCI registries: retrieve container image information, list tags and more.
abox.toolsio.github.A-Box-of-Tools/abox-tools
Process images and PDFs, inspect or remove image metadata, and calculate local file checksums.
Duelpilotcom.duelpilot/duelpilot
A/B testing on autopilot, run by your own AI agent: find ideas, design variants, read results.
RooYuncom.rooyun/rooyun
AI comic & short-drama studio: scripts to storyboards, image/video generation on an infinite canvas
drop.mediamedia.drop/mcp
Host files and AI-generated images on drop.media and get public or expiring private links.
Fashio AIcom.fashiolabs/fashio
On-model and ghost-mannequin fashion photos from a product photo. Spends credits; needs an API key.
Voice MCPgithub.com/mbailey/voice-mcp
Voice interaction: speech-to-text, text-to-speech and real-time voice conversations via local microphone, OpenAI-compatible APIs and LiveKit.
CraftStoryio.github.itseez3d/craftstory-mcp
Talking-avatar videos from a photo, short clips with sound, images and music.
Vidofyai.vidofy/mcp
Generate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.
atx-mcpio.github.gridhra/atx-mcp
Deterministic, non-generative image transform MCP server: reproducible recipes, immutable originals.
Veevid AIai.veevid/veevid
Generate AI videos, images and audio on Veevid with Kling 4.0, Seedance 2.5, Veo 3.1 and more.
Emeroio.github.EmeroAI/emero
Teach your AI assistant to make pro images, video, music and speech with every top model
Image to Text OCRio.github.sumitrmardy/image-to-text-ocr
OCR text from image URLs, 30 languages, lines with boxes. One flat row per image. Billed on text.
Instavar Video Templates and Studiocom.instavar/mcp-server
Free Remotion video templates and creative guides; optional hosted Studio rendering and publishing.
Frankai.hifrank/frank
AI-moderated voice interviews with your customers, delivering themes and insights
GrooveSheetnet.groovesheet/mcp
Find AI-transcribed sheet music, MIDI and stems for songs. /mcp/public needs no sign-in.
Prefireio.github.BarredEwe/prefire
Render SwiftUI #Preview as PNG images, so an AI agent sees the views it changes
Revanasi.revana/revana
Cheap AI video from your agent: Seedance 2.5 video and Nemesis clip restaging on prepaid credits.
EPW.toolsio.github.carlobianchi89/epwtools
EnergyPlus weather files (EPW, DDY, STAT) and design conditions for any site, OpenStudio-MCP ready.
AIGEws.aige/antix
AI creative studio for images, video and carousel decks, with one saved character in every shot.
Flow Music MCP Server by useapi.net (third-party)net.useapi/flowmusic
Google Flow Music (Lyria): songs, lyrics, extend, cover, remix, effects, stems
Mureka MCP Server by useapi.net (third-party)net.useapi/mureka
Mureka AI music: songs, lyrics, stems, sheet music, your own voice as a singer, speech
Gemini Notebook (NotebookLM) MCP Server by useapi.net (third-party)net.useapi/gemini-notebook
Google Gemini Notebook (NotebookLM): notebooks, sources, cited chat, podcasts, video, slides
Google Vids MCP Server by useapi.net (third-party)net.useapi/google-vids
Google Vids: Gemini Omni video with sound, voiced avatars, extend, upscale, edit, images
Kling AI MCP Server by useapi.net (third-party)net.useapi/kling
Kling AI: 4.0, v3 and Omni video, images, avatars, lip-sync, motion control, elements, voices
Google Flow Agent MCP Server by useapi.net (third-party)net.useapi/google-flow
Google Flow's agent: chat that plans and makes images and videos, approvals, your own media
Eclipse Loft MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/eclipse-loft-mcp
Governed design-to-print authority for agents — signed provenance from model to machine, safety
Eclipse Voice Core MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/voice-core
The Consent Registry and Number Registry every Eclipse telephony adapter obeys.
Eclipse Proof MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/proof
Governed video production — Herald-signed approval pins over exact edit states, hash-pinned
Eclipse Cluster MCPio.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/cluster
Signed images, governed runtimes — the gate runs first: no verified signature and provenance, no
AdCreator AI: Ad Creative Makercom.adcreator-ai/generate-ad-headlines
Turn a product photo into a finished ad image with copy, or get 10 ad headlines. Free, no signup.
NiceVoiscom.nicevois/rvc-training
Free stem, vocal, noise, reverb and format tools. Train RVC voices; convert vocals and whole songs.
Polymationio.github.paradoxsyn/rivemcp
Author Rive; convert Lottie, After Effects, Animate and Figma into it; animate AI and pixel art.
오늘냥이 (Oneul Nyangi)today.nyangi/oneul-nyangi
Real cat photos, diaries, profiles, age and food reference calculators, and breeds.
Imaginoucom.imaginou/imaginou
AI product videos from photos: showroom, presenter and comedic campaigns with storyboard approval.
Open Ephemeriscom.openephemeris/open-ephemeris
Sub-arcsecond astrology on NASA JPL DE440: natal, transits, Human Design, Vedic, BaZi.
b123d-printio.github.KD5RYN/b123d-print
Vibe CAD for 3D printing: design, check and export printable parts with build123d.
Euipoio.github.pipeworx-io/euipo
EUIPO MCP — EU trademarks, registered Community designs, and the shared reference registers the…
ClipAIio.github.isi1314/clipai-mcp
Turn long videos into scored, captioned 9:16 clips and schedule them to social platforms.
MCP Video Analyzergithub.com/guimatheus92/mcp-video-analyzer
Video analysis: extract transcripts, key frames, OCR text and annotated timelines from Loom links and direct MP4 or WebM files.
Reaper MCPgithub.com/xDarkzx/Reaper-MCP
Music production in REAPER: transport, tracks, MIDI editing, mixing and FX, tempo maps, markers and regions, and ReaScript execution.
2ankinet.2anki/mcp
Turn text, files, URLs, or photos into Anki flashcard decks from your AI assistant.
Transcribe (speech-to-text)co.youraitools/transcribe
Pay-per-minute speech-to-text: audio URL to text, SRT or VTT. Paid via x402 or credits.
Sklarstad Storefrontio.github.emersonsklar/sklarstad-storefront
Sklarstad products for AI agents: FirstTake, free open-source video production, shoot to master.
convert.expressexpress.convert/transcribe
Transcribe audio and video to text, SRT or VTT. Summaries, translation. Optional OAuth sign-in.
TopAIMuza.plpl.topaimuza/ranking
Chart and catalogue of Polish AI-generated music: artists, tracks, genres, new releases.
FrameAnyPhotocom.frameanyphoto/prints
Shop for and buy framed museum-quality prints of public-domain art and photos, shipped US-wide.
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.