Magnific
Magnific in natural language: upscale images, generate and list your creations. Connect your Magnifi
| Endpoint | https://api.mcp.ai/p_magnific (streamable-http) |
|---|---|
| Registry version | 0.1.0 |
| Now | 67 tools · grade D (59) · pin ts_2c26e31764285ed069b24acda36dfe14 · protocol 2025-06-18 |
| First / last listed | 2026-10-31 00:26 UTC / 2026-10-31 00:26 UTC |
| Grade over time | 2026-10-31: D (59), 67 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: magnific_account_balance magnific_creations_wait magnific_creations_get magnific_creations_search magnific_creations_list magnific_creations_request_upload magnific_creations_finalize_upload magnific_creations_upload_image magnific_creations_upload_file magnific_creations_move magnific_creations_like magnific_creations_comment magnific_folders_list magnific_folders_get magnific_folders_create magnific_folders_rename magnific_folders_delete magnific_project_report magnific_spaces_list magnific_spaces_create magnific_spaces_state magnific_spaces_get_nodes magnific_spaces_run magnific_spaces_run_status magnific_spaces_edit magnific_spaces_edit_status magnific_images_generate magnific_images_remove_background magnific_images_upscale magnific_images_skin_enhancer magnific_images_relight magnific_images_change_camera magnific_images_variations magnific_images_crop magnific_images_resize magnific_images_to_svg magnific_images_generate_svg magnific_images_models_list magnific_library_list magnific_library_create magnific_models3d_generate magnific_video_plan magnific_video_generate magnific_video_models_list magnific_video_upscale magnific_video_upscale_models_list magnific_video_concatenate magnific_video_speak magnific_audio_tts magnific_audio_music_generate magnific_audio_voices_list magnific_design_auto_resize magnific_design_auto_layers magnific_flows_list magnific_flows_get magnific_flows_run magnific_flows_wait magnific_stock_search magnific_stock_get magnific_stock_download magnific_stock_to_creation show_version report_bug connect toolkit_info marketplace authenticate
magnific_account_balance | User plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history. params: none |
magnific_creations_wait | Long-poll 1..8 creations until terminal or `timeoutSeconds` (default 25, max 25). In-progress entries get `poll_after_seconds` for the next call. params: identifiers*, timeoutSeconds |
magnific_creations_get | Single creation complete data — metadata + URLs (`url` full-res, `previewUrl` ~1024px, `thumbnailUrl` ~400px). params: creationIdentifier* |
magnific_creations_search | Search user creations as raw TOON text. Use `creations_get` for one id. `reference` required with from=folder/project-root. Defaults: history, page 1. params: from, reference, query, page, folderReference, fileType, toolNames, excludeToolNames |
magnific_creations_list | Filterable gallery widget (image/video/audio). Use instead of `creations_search` when user wants to browse their library. params: from, reference, query, fileType, toolNames |
magnific_creations_request_upload | Step 1 for local/user files: get presigned PUT URL(s). Upload bytes outside MCP, then call `creations_finalize_upload`. params: mimeType*, count |
magnific_creations_finalize_upload | Step 2 after PUT from `creations_request_upload`: convert temp path(s) to creations. Images <=25MB, videos <=200MB. params: path, uploads |
magnific_creations_upload_image | Upload public image URL in one step. For local/user files use `creations_request_upload` then `creations_finalize_upload`. params: url* |
magnific_creations_upload_file | 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`. params: file* |
magnific_creations_move | Move creations into `targetFolderReference`. Identifiers from `images_generate`/`creations_search`. Foreign identifier → abort. Target folder must belong to user. params: targetFolderReference*, creationIdentifiers* |
magnific_creations_like | Toggle heart/favorite reaction on a user-owned creation. params: creationIdentifier*, folderReference*, unlike |
magnific_creations_comment | Add a comment (or reply) to a user-owned creation. params: creationIdentifier*, folderReference*, text*, replyToCommentId |
magnific_folders_list | List folders/projects as raw TOON text. No params=top level; `onlyProjects`=projects; `parentReference`=children. Refs work with creations/folder tools. params: parentReference, onlyProjects, page |
magnific_folders_get | Fetch folder metadata by `reference`. Use before `creations_search` (`from=folder`). Foreign refs error. params: reference* |
magnific_folders_create | Create folder/project. No `parentReference`: workspace root. `type` defaults: project at root, folder when nested. params: name*, parentReference, type |
magnific_folders_rename | Rename a folder by `reference`. params: reference*, name* |
magnific_folders_delete | Move a folder and its files to trash. params: reference* |
magnific_project_report | English markdown status report for a project/folder. Last 7 days default, max 30. params: reference*, days |
magnific_spaces_list | Lean spaces catalog as raw TOON text. Share each `webUrl`; call `spaces_show` only for inline canvas preview. Do not use `creations_search`. params: query, ownership, page, perPage |
magnific_spaces_create | Create empty Space. Share `space.webUrl`; only call `spaces_show` when inline preview is requested. params: name*, description |
magnific_spaces_state | 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. params: spaceId*, selectedElementIds, selectedConnectionIds, currentPageId, pageId, scope |
magnific_spaces_get_nodes | Read-only. Like `spaces_state` but scoped to `nodeIds` + their connections. Cheaper than full board. Needs view perm. params: spaceId*, nodeIds*, currentPageId |
magnific_spaces_run | Run Space workflow from `startNodeId`. Modes: singular, connected default, downstream. Poll with `spaces_run_status`. params: spaceId*, startNodeId*, mode |
magnific_spaces_run_status | Poll `spaces_run`. `timeoutSeconds` long-polls up to 25s. In-progress returns `poll_after_seconds`; terminal call `creations_show`. params: workflowRunIdentifier*, timeoutSeconds |
magnific_spaces_edit | External MCP only. Start headless Space edit. Poll `spaces_edit_status` until allTerminal, then verify with `spaces_state`. params: query*, spaceId*, threadId, selectedElementIds, selectedConnectionIds, anchorElementId, anchorDirection |
magnific_spaces_edit_status | Wait for `spaces_edit` like `creations_wait`: long-polls up to `timeoutSeconds` (default 25, max 25). Snapshot-only when 0. Terminal → `spaces_state`. params: operationId, threadId, runId, timeoutSeconds |
magnific_images_generate | 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. params: prompt*, mode, aspectRatio, references, count, resolution, quality, folderReference |
magnific_images_remove_background | Cut-out subject on transparent PNG. Color BG: `images_color_background`. AI scene: `images_generate` with reference + prompt "replace the background with X". params: creationIdentifier*, folderReference |
magnific_images_upscale | AI upscale 2x/4x (Magnific, premium). Exact pixels: `images_resize`. Aspect: `images_crop`. Default scale=2. params: creationIdentifier*, scale, folderReference |
magnific_images_skin_enhancer | AI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0. params: creationIdentifier*, version, sharpen, smartGrain, skinDetail, optimizedFor, folderReference |
magnific_images_relight | AI relight. 1-4 lights with azimuth/elevation enums, type neutral|gel, intensity 1-10. Gel uses hex `color`. params: creationIdentifier*, lights*, resolution, numImages, folderReference |
magnific_images_change_camera | Reframe camera around subject. Defaults: rotate=45, vertical=0, closeup=5. params: creationIdentifier*, rotate, vertical, closeup, folderReference |
magnific_images_variations | Generate image-variation grid. Modes: angles|demographics|expressions|age|storyboard|custom. Defaults: angles, 3x3, 1:1, 4k. params: creationIdentifier*, variationMode, prompt, gridRows, gridCols, aspectRatio, resolution, selectedAngles, selectedEthnicities, selectedGenders, folderReference |
magnific_images_crop | 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. params: creationIdentifier*, aspectRatio*, folderReference |
magnific_images_resize | 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. params: creationIdentifier*, width*, height*, folderReference |
magnific_images_to_svg | Trace raster creation into SVG. New vector from prompt: `images_generate_svg`. params: creationIdentifier*, folderReference |
magnific_images_generate_svg | Text-to-SVG (Recraft v4 Pro Vector). Raster: `images_generate`. Trace existing raster: `images_to_svg`. Default aspectRatio=1:1. params: prompt*, aspectRatio, folderReference |
magnific_images_models_list | TTI model catalog as lean TOON text. `search` filters by name, slug, description, or tags. params: search, onlyRecommended |
magnific_library_list | Lean library catalog (characters, styles, elements, locations) for agent reasoning. Picker assets use library://. params: scope, type, page, perPage, search |
magnific_library_create | 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. params: name*, type*, description, gender, productType, images* |
magnific_models3d_generate | Image-to-3D GLB. Upload external images first. Animate with `models3d_rig`. Models: tripo-p1 default, tripo-v31, trellis-2. params: creationIdentifier*, model, resolution, textureQuality, faceLimit, folderReference |
magnific_video_plan | 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. params: prompt*, durationHint, styleHint, aspectRatioHint, referenceIdentifiers |
magnific_video_generate | 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 or a creation `identifier`; never `webUrl`. Limits: `video_models_list`. On UI-capable clients, aft params: video*, folderReference |
magnific_video_models_list | 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. params: search, onlyRecommended |
magnific_video_upscale | Upscale video via Topaz or Magnific. Pass `creationIdentifier` or Freepik `videoUrl`. Params: `video_upscale_models_list`. Then call `creations_show`. params: creationIdentifier, videoUrl, mode*, upscaleFactor, targetFps, targetResolution, focus, sharpen, enhancementModel, frameInterpolation, creativity, magnificResolution, premiumQuality, fpsBoost, smartGrain, flavor, turbo, preview, strength, folderReference |
magnific_video_upscale_models_list | Video upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums. Read before calling `video_upscale`. params: none |
magnific_video_concatenate | 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. params: name, creationIdentifiers*, folderReference |
magnific_video_speak | 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`. params: audioUrl*, videoUrl, imageUrl, mode, resolution, prompt, voiceId, folderReference |
magnific_audio_tts | 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). params: text*, voiceId, speakers, model, stability, similarityBoost, speed, useSpeakerBoost, temperature, systemInstruction, visible, folderReference |
magnific_audio_music_generate | 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. params: prompt*, model, durationSeconds, instrumental, folderReference |
magnific_audio_voices_list | TTS voice catalog as raw TOON text, no UI. Lean entries without preview URLs. Optional `search` filters by name, description, gender, or language. params: search |
magnific_design_auto_resize | Create resized design pages from an image. Use directly when ratios/social formats are known; otherwise show `design_auto_resize_show`. params: creationIdentifier*, aspectRatios*, name, textLayers, imageLayers, numLayers, multipage |
magnific_design_auto_layers | Extract editable layers from a flat image into a Pikaso design. params: creationIdentifier*, name, numLayers, vectorize |
magnific_flows_list | 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. params: query, ownership, page, perPage |
magnific_flows_get | 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`. params: identifier* |
magnific_flows_run | 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`. params: identifier*, inputs* |
magnific_flows_wait | Long-poll a `flows_run`. Terminal: one entry per output creation with real `identifier` for `creations_show`. In-progress: `poll_after_seconds`. params: workflowRunIdentifier*, timeoutSeconds |
magnific_stock_search | 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. params: query*, content_type, page, per_page |
magnific_stock_get | Full details for a single Freepik stock item: preview URL, dimensions, formats, author.
Bulk support: accepts ids for batched execution. params: id*, type, ids |
magnific_stock_download | 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. params: id*, type, folder_reference, ids |
magnific_stock_to_creation | Convert Freepik stock item → Pikaso creation. Use after user selects from stock_show.
Bulk support: accepts ids for batched execution. params: id*, folder_reference, title, ids |
show_version | Show the current MCP platform and adapter versions. params: none |
report_bug | Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction. params: message*, context, conversation |
connect | 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. params: none |
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. params: none |
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. params: action, query, mcp_id, limit, tier_slug, immediate, cancel_reason, cancel_comment, message, report_context, conversation, request_name, request_details, tool_id, arguments, prompt_slug, prompt_vars, prompt_category, prompt_tool, prompt_title, prompt_description, prompt_body, prompt_targets |
authenticate | 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. params: token |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.