Annuaire des serveurs MCP
53,197 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
- 33,630 serveurs distants
- Mis à jour toutes les heures
Agent Pattern MCPio.github.olk/agent-pattern-mcp
MCP server that provides AI agent pattern expertise for designing agent systems
Muxgithub.com/muxinc/mux-node-sdk/tree/master/packages/mcp-server
Mux is a video API for developers. With Mux's official MCP you can upload videos, create live streams, generate thumbnails, add captions, manage playback pol...
Saccadeio.github.Tavrin/saccade
Perceptual visual regression, image evidence inspection and bounded decision proposals.
Rialio.rial/mcp
Request photos by link and verify they are real: templates, verifications and verdicts.
PrintGenai.printgen/mcp
PrintGen makes custom apparel from an idea or a photo, with previews and a hosted checkout link.
Vaybelcom.vaybel/mcp
Vaybel turns apparel ideas into designs and mockups through a public MCP server and agent skills.
Telenow — AI Phone Calls & Voice Agentsai.telenow/telenow
Place phone calls, run calling campaigns and build voice agents from your own Telenow numbers.
Rightisio.github.Backers-Shawn/rightis
Identity-rights registry lookups before AI generation: is a face, voice or persona registered?
Playheadcom.tryplayhead/playhead
Watches a video or ad from a link and answers in words, with the second of every moment.
Your Move Exercise Video APIapp.ymove/exercise-api
1,413+ HD exercise videos with muscles and instructions, plus workout and program generation.
Tanod MLdev.tanod/ml
Local ML: speech to text (SRT/VTT), text embeddings, reranking, similarity, entities, zero-shot.
Audio File MCP Appio.github.counterpoint-studio/audio-file-mcp-app
Inspect local audio files — playback, metadata, loudness, spectrogram.
Neumeio.neume/neume
Make songs, change one part's lyrics in the same voice, and reimagine songs in new styles.
Local Whisperio.github.OrihuelaConde/local-whisper-mcp
Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.
Private AI Media Generationcom.livepairai/livepair-hub
Paid AI image/video generation for agents — x402 USDC or API key, no account needed.
Photo Scoutio.github.impanyu/photo-scout
Find nearby photo spots using real street imagery, visual scores and camera headings.
MagicON RF Design Enginesio.github.magiccadai/magicon
TX/RX/T-R chains, OTA link, radar, PCB filters, patch antennas, stackup, thermal, PDN, compliance.
ModCardfun.modcard/modcard
Find, personalize, share, and mail animated greeting cards with original music.
Sequencermedia.sequencer/sequencer
Create AI images, video, and audio, quote generation costs, and edit Sequencer projects.
Templatedio.github.templated-io/mcp-server-templated
Generate images, videos and PDFs from templates. Manage templates, folders, uploads and fonts.
Cocuyoai.cocuyo/cocuyo
Quote and create AI images and videos with existing Cocuyo credits and explicit confirmation.
HEA-Benchio.github.dfieser/hea-bench
High-entropy alloy and oxide descriptors, phase rules, corpus, properties, and design tools.
Recolor the Pastcom.crowfoundry/recolor-the-past
Colorize and restore photos, manage the library, and use account credits.
AINDFio.github.0design/aindf
Read-only MCP server for one AINDF design-system bundle: look up what it offers, validate screens.
Smiaio.github.Smia-Technologies-AS/smia
Build your own tools from chat: design, test and host them on a shareable MCP server URL.
Image OCR Extractor (Apify Actor)io.github.truhojunbot-tech/image-ocr-extractor
OCR text from images and scanned PDFs; pay-per-event via your Apify account.
Tanod Imagesdev.tanod/images
Image toolkit: resize, convert, compress, crop, metadata, hashes, favicons, OCR, QR codes, barcodes.
AI3D Studiostudio.ai3d/ai3d-studio
Generate 3D models from images or text with AI, then retexture or convert them to STL, 3MF or OBJ.
noslopUIcom.noslopui/noslopui
Hand-crafted UI components and design systems for agents, so builds don't look like AI slop.
MACKORN Hydraulic Cone Crusher Selectioncn.mackorn/mackorn-cone-crusher
MACKORN hydraulic cone crusher selection and crushing-plant design. 21 tools, callable over HTTP.
Giggy Speech MCPio.github.GRQDigitalCapital/giggy-mcp
Giggy speech tools for AI agents: discover voices and generate text-to-speech.
Klo - video editorcom.getklo.mcp/klo
Edit videos in the cloud: footage, color grading, audio, editable Remotion graphics and exports.
Brayercom.usebrayer/brayer
Design mockups, device frames and launch graphics live in your open Brayer studio tab.
Premiere Claude Bridgeio.github.koptsev63/premiere-claude-bridge
Assistant editor for Premiere Pro and DaVinci Resolve: logs, transcribes, rough cuts, subtitles, QC
PixelDojoai.pixeldojo/mcp
Generate images, video, audio and short films with 140+ AI models from any MCP client.
Kinetunecom.kinetune/kinetune
Lyric videos and Spotify Canvas loops from your songs, quoted in credits before anything runs.
PaKi Curatores.cesaryague/paki-curator
Catalogue agent for César Yagüe's silent moving-image works, intuitively crafted, never generated.
Zapsdesign.zaps/zaps
Photos and a brief in, finished social-media designs out. First design free, no account.
TrackForgestudio.trackforge/music-registration-check
Check a catalogue against The MLC, look up a song's writers, publishers and ISWC, validate CWR files
Ulule — Crowdfundingcom.ulule/mcp-public
Crowdfunding on Ulule: submit a project proposal, then build its page, goal, images and rewards.
Sydiumcom.sydium/sydium
Draft, schedule and publish social posts in your own voice across 11 platforms.
Textile Designer AIai.textile-designer/mcp
Textile design AI: print-ready upscaling, seamless repeats, colourways, screen separation.
PanoOn Street Viewio.github.fanrj3/panoon-mcp
Scan Street View areas into PanoIDs and download imagery through PanoOn.
Cooloursltd.perpetualsummer/coolours
Turn AI-designed colour palettes into Coolours links, with colour names, CSS and contrast checks
ditto.audioaudio.ditto/tts
Text-to-speech: browse voices and synthesize natural speech from text with ditto.audio.
Performance Atlascom.creatinginai/performance-atlas
Acting direction for AI video and voice: state-based behaviour kits and a free prompt linter.
Pixeverapp.pixever/mcp
Collective, moderated event photo spaces: read status, list media, save a guest photo, react, star.
Vidrenocom.vidreno/mcp
Publish films, monetise them, earn money, and host and embed videos on sites and apps.
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.