MCP server

Magnific

io.github.mcp-dir/magnific-mcp

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Magnific in natural language: upscale images, generate and list your creations. Connect your Magnifi

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

67

Token cost

About 10,481 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http magnific-mcp https://api.mcp.ai/p_magnific

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.magnific-mcp]
url = "https://api.mcp.ai/p_magnific"

Gemini CLI

{"mcpServers":{"magnific-mcp":{"httpUrl":"https://api.mcp.ai/p_magnific"}}}

Cursor

{"mcpServers":{"magnific-mcp":{"url":"https://api.mcp.ai/p_magnific"}}}

VS Code

{"servers":{"magnific-mcp":{"type":"http","url":"https://api.mcp.ai/p_magnific"}}}

Antigravity

agy mcp add magnific-mcp https://api.mcp.ai/p_magnific

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"magnific-mcp","server_url":"https://api.mcp.ai/p_magnific","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"magnific-mcp","server_url":"https://api.mcp.ai/p_magnific"}

Tools

• magnific_account_balance ~91 tokens
  User plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history.
• magnific_audio_music_generate ~182 tokens
  AI 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.
• magnific_audio_tts ~260 tokens
  TTS voiceover. Single (voiceId) or 2-speaker (speakers). ElevenLabs/Google. No voiceId? Call `audio_voices_show` first (or `audio_voices_list` for agent-only lookup).
• magnific_audio_voices_list ~94 tokens
  TTS voice catalog as raw TOON text, no UI. Lean entries without preview URLs. Optional `search` filters by name, description, gender, or language.
• magnific_creations_comment ~115 tokens
  Add a comment (or reply) to a user-owned creation.
• magnific_creations_finalize_upload ~119 tokens
  Step 2 after PUT from `creations_request_upload`: convert temp path(s) to creations. Images <=25MB, videos <=200MB.
• magnific_creations_get ~96 tokens
  Single creation complete data — metadata + URLs (`url` full-res, `previewUrl` ~1024px, `thumbnailUrl` ~400px).
• magnific_creations_like ~104 tokens
  Toggle heart/favorite reaction on a user-owned creation.
• magnific_creations_list ~173 tokens
  Filterable gallery widget (image/video/audio). Use instead of `creations_search` when user wants to browse their library.
• magnific_creations_move ~137 tokens
  Move creations into `targetFolderReference`. Identifiers from `images_generate`/`creations_search`. Foreign identifier → abort. Target folder must belong to user.
• magnific_creations_request_upload ~133 tokens
  Step 1 for local/user files: get presigned PUT URL(s). Upload bytes outside MCP, then call `creations_finalize_upload`.
• magnific_creations_search ~217 tokens
  Search user creations as raw TOON text. Use `creations_get` for one id. `reference` required with from=folder/project-root. Defaults: history, page 1.
• magnific_creations_upload_file Changes files · ~182 tokens
  Import 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`.
• magnific_creations_upload_image ~93 tokens
  Upload public image URL in one step. For local/user files use `creations_request_upload` then `creations_finalize_upload`.
• magnific_creations_wait ~119 tokens
  Long-poll 1..8 creations until terminal or `timeoutSeconds` (default 25, max 25). In-progress entries get `poll_after_seconds` for the next call.
• magnific_design_auto_layers ~108 tokens
  Extract editable layers from a flat image into a Pikaso design.
• magnific_design_auto_resize ~168 tokens
  Create resized design pages from an image. Use directly when ratios/social formats are known; otherwise show `design_auto_resize_show`.
• magnific_flows_get ~110 tokens
  Flow input/output spec as raw TOON text. Each input includes a normalized `kind`, `howToProvide`, and resolved `options`/`presetOptions` where applicable. Call before `flows_run`.
• magnific_flows_list ~127 tokens
  Flows 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.
• magnific_flows_run ~148 tokens
  Run 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`.
• magnific_flows_wait ~116 tokens
  Long-poll a `flows_run`. Terminal: one entry per output creation with real `identifier` for `creations_show`. In-progress: `poll_after_seconds`.
• magnific_folders_create ~106 tokens
  Create folder/project. No `parentReference`: workspace root. `type` defaults: project at root, folder when nested.
• magnific_folders_delete Deletes data · ~70 tokens
  Move a folder and its files to trash.
• magnific_folders_get ~88 tokens
  Fetch folder metadata by `reference`. Use before `creations_search` (`from=folder`). Foreign refs error.
• magnific_folders_list ~114 tokens
  List folders/projects as raw TOON text. No params=top level; `onlyProjects`=projects; `parentReference`=children. Refs work with creations/folder tools.
• magnific_folders_rename ~77 tokens
  Rename a folder by `reference`.
• magnific_images_change_camera ~122 tokens
  Reframe camera around subject. Defaults: rotate=45, vertical=0, closeup=5.
• magnific_images_crop ~143 tokens
  Center-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.
• magnific_images_generate ~269 tokens
  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 `creations_show` with all identifiers; never stop at links.
• magnific_images_generate_svg ~137 tokens
  Text-to-SVG (Recraft v4 Pro Vector). Raster: `images_generate`. Trace existing raster: `images_to_svg`. Default aspectRatio=1:1.
• magnific_images_models_list ~89 tokens
  TTI model catalog as lean TOON text. `search` filters by name, slug, description, or tags.
• magnific_images_relight ~207 tokens
  AI relight. 1-4 lights with azimuth/elevation enums, type neutral|gel, intensity 1-10. Gel uses hex `color`.
• magnific_images_remove_background ~123 tokens
  Cut-out subject on transparent PNG. Color BG: `images_color_background`. AI scene: `images_generate` with reference + prompt "replace the background with X".
• magnific_images_resize ~144 tokens
  Resize 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.
• magnific_images_skin_enhancer ~198 tokens
  AI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0.
• magnific_images_to_svg ~97 tokens
  Trace raster creation into SVG. New vector from prompt: `images_generate_svg`.
• magnific_images_upscale ~118 tokens
  AI upscale 2x/4x (Magnific, premium). Exact pixels: `images_resize`. Aspect: `images_crop`. Default scale=2.
• magnific_images_variations ~271 tokens
  Generate image-variation grid. Modes: angles|demographics|expressions|age|storyboard|custom. Defaults: angles, 3x3, 1:1, 4k.
• magnific_library_create ~191 tokens
  Create 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.
• magnific_library_list ~139 tokens
  Lean library catalog (characters, styles, elements, locations) for agent reasoning. Picker assets use library://.
• magnific_models3d_generate ~169 tokens
  Image-to-3D GLB. Upload external images first. Animate with `models3d_rig`. Models: tripo-p1 default, tripo-v31, trellis-2.
• magnific_project_report ~90 tokens
  English markdown status report for a project/folder. Last 7 days default, max 30.
• magnific_spaces_create ~94 tokens
  Create empty Space. Share `space.webUrl`; only call `spaces_show` when inline preview is requested.
• magnific_spaces_edit ~179 tokens
  External MCP only. Start headless Space edit. Poll `spaces_edit_status` until allTerminal, then verify with `spaces_state`.
• magnific_spaces_edit_status ~122 tokens
  Wait for `spaces_edit` like `creations_wait`: long-polls up to `timeoutSeconds` (default 25, max 25). Snapshot-only when 0. Terminal → `spaces_state`.
• magnific_spaces_get_nodes ~120 tokens
  Read-only. Like `spaces_state` but scoped to `nodeIds` + their connections. Cheaper than full board. Needs view perm.
• magnific_spaces_list ~123 tokens
  Lean spaces catalog as raw TOON text. Share each `webUrl`; call `spaces_show` only for inline canvas preview. Do not use `creations_search`.
• magnific_spaces_run ~124 tokens
  Run Space workflow from `startNodeId`. Modes: singular, connected default, downstream. Poll with `spaces_run_status`.
• magnific_spaces_run_status ~114 tokens
  Poll `spaces_run`. `timeoutSeconds` long-polls up to 25s. In-progress returns `poll_after_seconds`; terminal call `creations_show`.
• magnific_spaces_state ~180 tokens
  Read-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.
• magnific_stock_download ~144 tokens
  Signed download URL for a stock item. Pass folder_reference to also save as a creation (rate-limited). Bulk support: accepts ids for batched execution.
• magnific_stock_get ~126 tokens
  Full details for a single Freepik stock item: preview URL, dimensions, formats, author. Bulk support: accepts ids for batched execution.
• magnific_stock_search ~137 tokens
  Search Freepik stock catalog by keyword. Returns items with IDs, titles, types, preview URLs. Use stock_get for full details, stock_download for file URL.
• magnific_stock_to_creation ~127 tokens
  Convert Freepik stock item → Pikaso creation. Use after user selects from stock_show. Bulk support: accepts ids for batched execution.
• magnific_video_concatenate ~138 tokens
  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.
• magnific_video_generate ~571 tokens
  Generate 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
• magnific_video_models_list ~108 tokens
  Video-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.
• magnific_video_plan ~164 tokens
  Call 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.
• magnific_video_speak ~225 tokens
  Make 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`.
• magnific_video_upscale ~353 tokens
  Upscale video via Topaz or Magnific. Pass `creationIdentifier` or Freepik `videoUrl`. Params: `video_upscale_models_list`. Then call `creations_show`.
• magnific_video_upscale_models_list ~95 tokens
  Video upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums. Read before calling `video_upscale`.

Browse

• GitHub tools
• ElevenLabs tools
• GitHub and code hosting
• Text to speech
• Music and audio

Related MCP servers

• Unifically
  One API for 100+ AI video, image, music and speech models.
• Pixfaro
  Generate images with any major model — one API key, one prepaid balance, one MCP.
• aicut
  Generate AI videos, images, audio and staged AI Video Story episodes, and publish them to social.
• Studiomcphub
  32 creative AI tools (18 free) for agents: generate, upscale, mockup, print, watermark.
• Maginary
  AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
• God Mode AI Sprite Generator
  Generate game sprite sheets and animations from an image, and clean up sprite backgrounds.
• StockCake
  Search millions of CC0 public-domain AI images: previews, dimensions, provenance, license.
• streetshirts
  Design custom T-shirts, preview artwork, personalize team shirts and prepare a checkout link.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.mcp-dir/magnific-mcp.svg)](https://aptlynx.net/servers/io.github.mcp-dir/magnific-mcp)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents