magnific_account_balance
User plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history.
Takes no parameters.

io.github.mcp-dirPublished by GitHub account mcp-dirv0.1.0Updated Nov 18, 2026
Magnific in natural language: upscale images, generate and list your creations. Connect your Magnifi
Connects an assistant to a Magnific account to generate and edit images, video and audio, upscale media, and manage the user's creations and folders.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.mcp-dir%2Fmagnific-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"magnific": {
"type": "http",
"url": "https://api.mcp.ai/p_magnific"
}
}
}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.
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 Cursor
➕ Instalar Magnific no VS Code
Funciona em qualquer cliente MCP que suporte MCP over HTTP. A URL do servidor é sempre:
Detalhes por cliente: INSTALL.md.
Detalhe de cada tool: docs/ferramentas.md
Grátis.
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.
Source: README.md at commit 37c07df
User plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history.
Takes no parameters.
Long-poll 1..8 creations until terminal or `timeoutSeconds` (default 25, max 25). In-progress entries get `poll_after_seconds` for the next call.
identifiersrequiredtimeoutSecondsSingle creation complete data — metadata + URLs (`url` full-res, `previewUrl` ~1024px, `thumbnailUrl` ~400px).
creationIdentifierrequiredSearch user creations as raw TOON text. Use `creations_get` for one id. `reference` required with from=folder/project-root. Defaults: history, page 1.
frompagequeryfileTypereferencetoolNamesfolderReferenceexcludeToolNamesFilterable gallery widget (image/video/audio). Use instead of `creations_search` when user wants to browse their library.
fromqueryfileTypereferencetoolNamesStep 1 for local/user files: get presigned PUT URL(s). Upload bytes outside MCP, then call `creations_finalize_upload`.
countmimeTyperequiredStep 2 after PUT from `creations_request_upload`: convert temp path(s) to creations. Images <=25MB, videos <=200MB.
pathuploadsUpload public image URL in one step. For local/user files use `creations_request_upload` then `creations_finalize_upload`.
urlrequiredImport a file the user attached in the host (e.g. a ChatGPT upload) as a creation, then use the returned identifier in image tools. Use this instead of asking for a URL when the user already uploaded a local file. For a public URL use `creations_upload_image`.
filerequiredMove creations into `targetFolderReference`. Identifiers from `images_generate`/`creations_search`. Foreign identifier → abort. Target folder must belong to user.
creationIdentifiersrequiredtargetFolderReferencerequiredToggle heart/favorite reaction on a user-owned creation.
unlikefolderReferencerequiredcreationIdentifierrequiredAdd a comment (or reply) to a user-owned creation.
textrequiredfolderReferencerequiredreplyToCommentIdcreationIdentifierrequiredList folders/projects as raw TOON text. No params=top level; `onlyProjects`=projects; `parentReference`=children. Refs work with creations/folder tools.
pageonlyProjectsparentReferenceFetch folder metadata by `reference`. Use before `creations_search` (`from=folder`). Foreign refs error.
referencerequiredCreate folder/project. No `parentReference`: workspace root. `type` defaults: project at root, folder when nested.
namerequiredtypeparentReferenceRename a folder by `reference`.
namerequiredreferencerequiredMove a folder and its files to trash.
referencerequiredEnglish markdown status report for a project/folder. Last 7 days default, max 30.
daysreferencerequiredLean spaces catalog as raw TOON text. Share each `webUrl`; call `spaces_show` only for inline canvas preview. Do not use `creations_search`.
pagequeryperPageownershipCreate empty Space. Share `space.webUrl`; only call `spaces_show` when inline preview is requested.
namerequireddescriptionRead-only board context, raw TOON. Default: current page + pageIndex (other pages, counts). pageId: another page on demand. scope=all: whole board (costly). selectedElementIds: selected nodes. Needs view perm.
scopepageIdspaceIdrequiredcurrentPageIdselectedElementIdsselectedConnectionIdsRead-only. Like `spaces_state` but scoped to `nodeIds` + their connections. Cheaper than full board. Needs view perm.
nodeIdsrequiredspaceIdrequiredcurrentPageIdRun Space workflow from `startNodeId`. Modes: singular, connected default, downstream. Poll with `spaces_run_status`.
modespaceIdrequiredstartNodeIdrequiredPoll `spaces_run`. `timeoutSeconds` long-polls up to 25s. In-progress returns `poll_after_seconds`; terminal call `creations_show`.
timeoutSecondsworkflowRunIdentifierrequiredExternal MCP only. Start headless Space edit. Poll `spaces_edit_status` until allTerminal, then verify with `spaces_state`.
queryrequiredspaceIdrequiredthreadIdanchorDirectionanchorElementIdselectedElementIdsselectedConnectionIdsWait for `spaces_edit` like `creations_wait`: long-polls up to `timeoutSeconds` (default 25, max 25). Snapshot-only when 0. Terminal → `spaces_state`.
runIdthreadIdoperationIdtimeoutSecondsGenerate/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 `creations_show` with all identifiers; never stop at links.
modecountpromptrequiredqualityreferencesresolutionaspectRatiofolderReferenceCut-out subject on transparent PNG. Color BG: `images_color_background`. AI scene: `images_generate` with reference + prompt "replace the background with X".
folderReferencecreationIdentifierrequiredAI upscale 2x/4x (Magnific, premium). Exact pixels: `images_resize`. Aspect: `images_crop`. Default scale=2.
scalefolderReferencecreationIdentifierrequiredAI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0.
sharpenversionskinDetailsmartGrainoptimizedForfolderReferencecreationIdentifierrequiredAI relight. 1-4 lights with azimuth/elevation enums, type neutral|gel, intensity 1-10. Gel uses hex `color`.
lightsrequirednumImagesresolutionfolderReferencecreationIdentifierrequiredReframe camera around subject. Defaults: rotate=45, vertical=0, closeup=5.
rotatecloseupverticalfolderReferencecreationIdentifierrequiredGenerate image-variation grid. Modes: angles|demographics|expressions|age|storyboard|custom. Defaults: angles, 3x3, 1:1, 4k.
promptgridColsgridRowsresolutionaspectRatiovariationModeselectedAnglesfolderReferenceselectedGenderscreationIdentifierrequiredselectedEthnicitiesCenter-crop to `aspectRatio`. Pixels: `images_resize`. AI upscale: `images_upscale`. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9.
aspectRatiorequiredfolderReferencecreationIdentifierrequiredResize to exact pixels (no AI). For real detail upscaling: `images_upscale` first. Aspect: `images_crop`. Dimensions snap to multiples of 8; center-crop on aspect mismatch.
widthrequiredheightrequiredfolderReferencecreationIdentifierrequiredTrace raster creation into SVG. New vector from prompt: `images_generate_svg`.
folderReferencecreationIdentifierrequiredText-to-SVG (Recraft v4 Pro Vector). Raster: `images_generate`. Trace existing raster: `images_to_svg`. Default aspectRatio=1:1.
promptrequiredaspectRatiofolderReferenceTTI model catalog as lean TOON text. `search` filters by name, slug, description, or tags.
searchonlyRecommendedLean library catalog (characters, styles, elements, locations) for agent reasoning. Picker assets use library://.
pagetypescopesearchperPageCreate a reusable library asset (character/product/location) from 1-6 images. Use the returned numeric `id` in generation refs (same id Spaces uses). No LoRA training.
namerequiredtyperequiredgenderimagesrequireddescriptionproductTypeImage-to-3D GLB. Upload external images first. Animate with `models3d_rig`. Models: tripo-p1 default, tripo-v31, trellis-2.
modelfaceLimitresolutiontextureQualityfolderReferencecreationIdentifierrequiredCall FIRST for any video request. Returns markdown plan: brief, open questions, characters to prepare, recommended model slug, prompt draft. Videos >15s: plan splits into clips + `video_concatenate` instructions.
promptrequiredstyleHintdurationHintaspectRatioHintreferenceIdentifiersGenerate video. External clients: call `video_plan` first to draft the brief and resolve model choice — skip only if the user explicitly says "just generate" or "one-shot". Pick a model with `slug` (copy it verbatim from `video_models_list`); omit `slug` for auto-select. Image refs: use an asset URL or a creation `identifier`; never `webUrl`. Limits: `video_models_list`. On UI-capable clients, after generating you MUST call `creations_show` once with all returned identifiers to render results; never stop at links.
videorequiredfolderReferenceVideo-gen model catalog as lean TOON text. `search` filters by name, slug, description, or tags. Run `video_plan` first — plan resolves slug to validate here.
searchonlyRecommendedUpscale video via Topaz or Magnific. Pass `creationIdentifier` or Freepik `videoUrl`. Params: `video_upscale_models_list`. Then call `creations_show`.
moderequiredfocusturboflavorpreviewsharpenfpsBooststrengthvideoUrltargetFpscreativitysmartGrain+8 moreVideo upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums. Read before calling `video_upscale`.
Takes no parameters.
Concatenate completed video creations into one MP4. Assembles multi-clip plans from `video_plan`. Audio from each clip; no external audio bed. Returns queued creation.
namefolderReferencecreationIdentifiersrequiredMake a character speak. Image+audio → talking head (Veed Fabric 1.0). Video+audio → lip sync (Lipsync 2.0). Omit `mode` for auto. Pass asset URLs or a creation `identifier` (from `audio_tts`, `images_generate`, `video_generate`). Then call `creations_show`.
modepromptvoiceIdaudioUrlrequiredimageUrlvideoUrlresolutionfolderReferenceTTS voiceover. Single (voiceId) or 2-speaker (speakers). ElevenLabs/Google. No voiceId? Call `audio_voices_show` first (or `audio_voices_list` for agent-only lookup).
textrequiredmodelspeedvisiblevoiceIdspeakersstabilitytemperaturefolderReferencesimilarityBoostuseSpeakerBoostsystemInstructionAI music generation. Google Lyria or ElevenLabs. Pass `prompt`, optional `model`/`durationSeconds`/`instrumental`. Lyria/Lyria-3 produce fixed 30s; Lyria-3-Pro accepts 30–180s; ElevenLabs accepts 10–300s.
modelpromptrequiredinstrumentaldurationSecondsfolderReferenceTTS voice catalog as raw TOON text, no UI. Lean entries without preview URLs. Optional `search` filters by name, description, gender, or language.
searchCreate resized design pages from an image. Use directly when ratios/social formats are known; otherwise show `design_auto_resize_show`.
namemultipagenumLayerstextLayersimageLayersaspectRatiosrequiredcreationIdentifierrequiredExtract editable layers from a flat image into a Pikaso design.
namenumLayersvectorizecreationIdentifierrequiredFlows catalog as raw TOON text, no UI. Lean entries without preview URLs. For an inline picker use flows_show; for a single flow input/output spec use flows_get.
pagequeryperPageownershipFlow input/output spec as raw TOON text. Each input includes a normalized `kind`, `howToProvide`, and resolved `options`/`presetOptions` where applicable. Call before `flows_run`.
identifierrequiredRun flow. `flows_get` first for input specs. `inputs` is `{inputId: value}` (creation inputs from `creations_list`, voices from `audio_voices_show`). Returns `workflowRunIdentifier` → `flows_wait` → `creations_show`.
inputsrequiredidentifierrequiredLong-poll a `flows_run`. Terminal: one entry per output creation with real `identifier` for `creations_show`. In-progress: `poll_after_seconds`.
timeoutSecondsworkflowRunIdentifierrequiredSearch Freepik stock catalog by keyword. Returns items with IDs, titles, types, preview URLs. Use stock_get for full details, stock_download for file URL.
pagequeryrequiredper_pagecontent_typeFull details for a single Freepik stock item: preview URL, dimensions, formats, author. Bulk support: accepts ids for batched execution.
idrequiredidstypeSigned download URL for a stock item. Pass folder_reference to also save as a creation (rate-limited). Bulk support: accepts ids for batched execution.
idrequiredidstypefolder_referenceConvert Freepik stock item → Pikaso creation. Use after user selects from stock_show. Bulk support: accepts ids for batched execution.
idrequiredidstitlefolder_referenceShow Version
Show the current MCP platform and adapter versions.
Takes no parameters.
Report Bug
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
contextmessagerequiredconversationConnection Status
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
Takes no parameters.
Toolkit Info
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
Takes no parameters.
Marketplace
The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
limitqueryactionmcp_idmessagetool_idargumentsimmediatetier_slugprompt_bodyprompt_slugprompt_tool+11 moreAuthenticate
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
token100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
https://api.mcp.ai/p_magnificFaça upscale dessa imagem no MagnificListe minhas criações recentes no MagnificGere uma variação dessa imagem no Magnific