Provides text-to-speech voiceover and AI music generation through ElevenLabs, including single or dual-speaker TTS and configurable music generation.
Enables searching, retrieving, downloading, and converting Freepik stock items into creations.
Provides text-to-speech and AI music generation using Google services, including Lyria music models.
Enables talking-head and lip-sync video generation using VEED's Fabric 1.0 and Lipsync 2.0 models.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Magnific Faça upscale desta imagem em 4x"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Magnific por linguagem natural: faça upscale de imagens, gere e liste suas criações. Conecte com sua conta Magnific e use os créditos do seu plano.
📊 61 ferramentas
✏️ Leitura e escrita
💬 Funciona com qualquer cliente MCP: Claude Desktop, Cursor, VS Code, Cline, Continue
🔑 Login via magic-link (sem senha)
English version · Documentação completa · Skill pra agentes
A Anthropic unificou a instalação de MCPs em claude.ai/customize/connectors. O mesmo link serve pra Claude Web e Claude Desktop (basta estar logado):
Manual (se o deeplink não abrir): claude.ai/customize/connectors → + → Adicionar conector personalizado → cole Nome Magnific e URL https://api.mcp.ai/p_magnific.
➕ Instalar Magnific no VS Code
Funciona em qualquer cliente MCP que suporte MCP over HTTP. A URL do servidor é sempre:
https://api.mcp.ai/p_magnificDetalhes por cliente: INSTALL.md.
Related MCP server: ImaginePro MCP Server
Faça upscale dessa imagem no Magnific
Liste minhas criações recentes no Magnific
Gere uma variação dessa imagem no MagnificTool | Descrição |
| User plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history. |
| Long-poll 1..8 creations until terminal or |
| Single creation complete data — metadata + URLs ( |
| Search user creations as raw TOON text. |
| Filterable gallery widget (image/video/audio). |
| Step 1 for local/user files: get presigned PUT URL(s). |
| Step 2 after PUT from |
| Upload public image URL in one step. |
| Import a file the user attached in the host (e.g. |
| Move creations into |
| Toggle heart/favorite reaction on a user-owned creation. |
| Add a comment (or reply) to a user-owned creation. |
| List folders/projects as raw TOON text. |
| Fetch folder metadata by |
| Create folder/project. No |
| Rename a folder by |
| Move a folder and its files to trash. |
| English markdown status report for a project/folder. |
| Lean spaces catalog as raw TOON text. |
| Create empty Space. Share |
| Read-only board context, raw TOON. |
| Read-only. Like |
| Run Space workflow from |
| Poll |
| External MCP only. Start headless Space edit. Poll |
| Wait for |
| Generate/edit images. No refs=TTI. references[] (max 12; see field docs). Defaults: mode=auto, ratio=1:1, count<=8. resolution/quality per images_models_list. UI clients: after generating, MUST call |
| Cut-out subject on transparent PNG. |
| AI upscale 2x/4x (Magnific, premium). |
| AI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0. |
| AI relight. 1-4 lights with azimuth/elevation enums, type neutral |
| Reframe camera around subject. |
| Generate image-variation grid. |
| Center-crop to |
| Resize to exact pixels (no AI). |
| Trace raster creation into SVG. |
| Text-to-SVG (Recraft v4 Pro Vector). |
| TTI model catalog as lean TOON text. |
| Lean library catalog (characters, styles, elements, locations) for agent reasoning. |
| Create a reusable library asset (character/product/location) from 1-6 images. |
| Image-to-3D GLB. Upload external images first. Animate with |
| Call FIRST for any video request. |
| Generate video. External clients: call |
| Video-gen model catalog as lean TOON text. |
| Upscale video via Topaz or Magnific. |
| Video upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums. |
| Concatenate completed video creations into one MP4. |
| Make a character speak. Image+audio → talking head (Veed Fabric 1.0). Video+audio → lip sync (Lipsync 2.0). Omit |
| TTS voiceover. Single (voiceId) or 2-speaker (speakers). ElevenLabs/Google. No voiceId? Call |
| AI music generation. Google Lyria or ElevenLabs. Pass |
| TTS voice catalog as raw TOON text, no UI. |
| Create resized design pages from an image. |
| Extract editable layers from a flat image into a Pikaso design. |
| Flows catalog as raw TOON text, no UI. |
| Flow input/output spec as raw TOON text. |
| Run flow. |
| Long-poll a |
| Search Freepik stock catalog by keyword. |
| Full details for a single Freepik stock item: preview URL, dimensions, formats, author. |
| Signed download URL for a stock item. |
| Convert Freepik stock item → Pikaso creation. |
Detalhe de cada tool: docs/ferramentas.md
Grátis.
Sub-processadores: Magnific (Freepik), o LLM host que você escolher (Claude, ChatGPT, Cursor, agente próprio). Lista completa em docs/privacidade-lgpd.md.
Os dados retornados pelas tools são enviados ao LLM host que você escolher, sub-processador fora do nosso controle. Recomendamos planos com opt-out de treinamento.
O servidor é open source? O servidor é proprietário (hosted). Este repositório é o wrapper público com manifestos, docs e skills — tudo MIT.
Posso usar com agente próprio (não Claude/Cursor)?
Sim — qualquer cliente que suporte MCP over HTTP. URL: https://api.mcp.ai/p_magnific.
MIT — veja LICENSE. O servidor MCP em api.mcp.ai/p_magnific é proprietário (hosted); este repositório (manifestos, docs, skills) é MIT.
This server cannot be deployed
Generate images with your own ChatGPT subscription (Plus, Pro or Team), without spending API credits
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Create AI images and videos, manage projects and credits, and use workspace campaign context.
Generate images, videos, voiceovers, and captions from a chat prompt.
