Magnific
Magnific in natural language: upscale images, generate and list your creations. Connect your Magnifi
我該用這個嗎
品質與安全性
發現項目（11）
- LOWTool 'magnific_creations_like' description lacks action verb在 magnific_creations_like 中
- LOWTool 'magnific_folders_rename' description lacks action verb在 magnific_folders_rename 中
- LOWTool 'magnific_video_concatenate' description lacks action verb在 magnific_video_concatenate 中
- LOWTool 'magnific_audio_music_generate' description lacks action verb在 magnific_audio_music_generate 中
- LOWTool 'magnific_design_auto_layers' description lacks action verb在 magnific_design_auto_layers 中
- LOWTool 'connect' description lacks action verb在 connect 中
- LOWTool 'magnific_creations_request_upload' name length outside 3-30 range在 magnific_creations_request_upload 中
- LOWTool 'magnific_creations_finalize_upload' name length outside 3-30 range在 magnific_creations_finalize_upload 中
- LOWTool 'magnific_creations_upload_image' name length outside 3-30 range在 magnific_creations_upload_image 中
- LOWTool 'magnific_images_remove_background' name length outside 3-30 range在 magnific_images_remove_background 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"magnific-mcp": {
"url": "https://api.mcp.ai/p_magnific"
}
}
}遠端端點
https://api.mcp.ai/p_magnificstreamable-http它能做什麼
工具清單
工具（67）
🟢magnific_account_balance
User plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_creations_wait(identifiers, timeoutSeconds)
Long-poll 1..8 creations until terminal or `timeoutSeconds` (default 25, max 25). In-progress entries get `poll_after_seconds` for the next call.
輸入結構描述
{
"type": "object",
"properties": {
"identifiers": {
"type": "array",
"items": {
"type": "string"
}
},
"timeoutSeconds": {
"type": "number"
}
},
"required": [
"identifiers"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_creations_get(creationIdentifier)
Single creation complete data — metadata + URLs (`url` full-res, `previewUrl` ~1024px, `thumbnailUrl` ~400px).
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_creations_search(from, reference, query, page, folderReference, ...)
Search user creations as raw TOON text. Use `creations_get` for one id. `reference` required with from=folder/project-root. Defaults: history, page 1.
輸入結構描述
{
"type": "object",
"properties": {
"from": {
"type": "string",
"enum": [
"history",
"folder",
"project-root",
"all-assets",
"favorites",
"downloads",
"trash",
"upload",
"v3-upload",
"v3-favorites",
"v3-trash"
]
},
"reference": {
"type": "string"
},
"query": {
"type": "string"
},
"page": {
"type": "number"
},
"folderReference": {
"type": "string"
},
"fileType": {
"type": "string",
"enum": [
"image",
"video",
"audio"
]
},
"toolNames": {
"type": "array",
"items": {
"type": "string"
}
},
"excludeToolNames": {
"type": "array",
"items": {
"type": "string"
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_creations_list(from, reference, query, fileType, toolNames)
Filterable gallery widget (image/video/audio). Use instead of `creations_search` when user wants to browse their library.
輸入結構描述
{
"type": "object",
"properties": {
"from": {
"type": "string",
"enum": [
"history",
"folder",
"project-root",
"all-assets",
"favorites",
"downloads",
"trash",
"upload",
"v3-upload",
"v3-favorites",
"v3-trash"
]
},
"reference": {
"type": "string"
},
"query": {
"type": "string"
},
"fileType": {
"type": "string",
"enum": [
"image",
"video",
"audio"
]
},
"toolNames": {
"type": "array",
"items": {
"type": "string"
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_creations_request_upload(mimeType, count)
Step 1 for local/user files: get presigned PUT URL(s). Upload bytes outside MCP, then call `creations_finalize_upload`.
輸入結構描述
{
"type": "object",
"properties": {
"mimeType": {
"type": "string",
"enum": [
"image/jpeg",
"image/png",
"image/webp",
"video/mp4",
"video/quicktime",
"video/webm",
"video/x-m4v"
]
},
"count": {
"type": "number"
}
},
"required": [
"mimeType"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_creations_finalize_upload(path, uploads)
Step 2 after PUT from `creations_request_upload`: convert temp path(s) to creations. Images <=25MB, videos <=200MB.
輸入結構描述
{
"type": "object",
"properties": {
"path": {
"type": "string"
},
"uploads": {
"type": "array",
"items": {
"type": "object",
"properties": {
"path": {
"type": "string"
}
},
"required": [
"path"
]
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_creations_upload_image(url)
Upload public image URL in one step. For local/user files use `creations_request_upload` then `creations_finalize_upload`.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string"
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_creations_upload_file(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`.
輸入結構描述
{
"type": "object",
"properties": {
"file": {
"type": "object",
"properties": {
"download_url": {
"type": "string"
},
"file_id": {
"type": "string"
},
"mime_type": {
"type": "string"
},
"file_name": {
"type": "string"
}
},
"required": [
"download_url",
"file_id"
]
}
},
"required": [
"file"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_creations_move(targetFolderReference, creationIdentifiers)
Move creations into `targetFolderReference`. Identifiers from `images_generate`/`creations_search`. Foreign identifier → abort. Target folder must belong to user.
輸入結構描述
{
"type": "object",
"properties": {
"targetFolderReference": {
"type": "string"
},
"creationIdentifiers": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"targetFolderReference",
"creationIdentifiers"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_creations_like(creationIdentifier, folderReference, unlike)
Toggle heart/favorite reaction on a user-owned creation.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"folderReference": {
"type": "string"
},
"unlike": {
"type": "boolean"
}
},
"required": [
"creationIdentifier",
"folderReference"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_creations_comment(creationIdentifier, folderReference, text, replyToCommentId)
Add a comment (or reply) to a user-owned creation.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"folderReference": {
"type": "string"
},
"text": {
"type": "string"
},
"replyToCommentId": {
"type": "string"
}
},
"required": [
"creationIdentifier",
"folderReference",
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_folders_list(parentReference, onlyProjects, page)
List folders/projects as raw TOON text. No params=top level; `onlyProjects`=projects; `parentReference`=children. Refs work with creations/folder tools.
輸入結構描述
{
"type": "object",
"properties": {
"parentReference": {
"type": "string"
},
"onlyProjects": {
"type": "boolean"
},
"page": {
"type": "number"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_folders_get(reference)
Fetch folder metadata by `reference`. Use before `creations_search` (`from=folder`). Foreign refs error.
輸入結構描述
{
"type": "object",
"properties": {
"reference": {
"type": "string"
}
},
"required": [
"reference"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_folders_create(name, parentReference, type)
Create folder/project. No `parentReference`: workspace root. `type` defaults: project at root, folder when nested.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"parentReference": {
"type": "string"
},
"type": {
"type": "string"
}
},
"required": [
"name"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_folders_rename(reference, name)
Rename a folder by `reference`.
輸入結構描述
{
"type": "object",
"properties": {
"reference": {
"type": "string"
},
"name": {
"type": "string"
}
},
"required": [
"reference",
"name"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴magnific_folders_delete(reference)
Move a folder and its files to trash.
輸入結構描述
{
"type": "object",
"properties": {
"reference": {
"type": "string"
}
},
"required": [
"reference"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_project_report(reference, days)
English markdown status report for a project/folder. Last 7 days default, max 30.
輸入結構描述
{
"type": "object",
"properties": {
"reference": {
"type": "string"
},
"days": {
"type": "number"
}
},
"required": [
"reference"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_spaces_list(query, ownership, page, perPage)
Lean spaces catalog as raw TOON text. Share each `webUrl`; call `spaces_show` only for inline canvas preview. Do not use `creations_search`.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"ownership": {
"type": "string",
"enum": [
"all",
"mine",
"shared"
]
},
"page": {
"type": "number"
},
"perPage": {
"type": "number"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_spaces_create(name, description)
Create empty Space. Share `space.webUrl`; only call `spaces_show` when inline preview is requested.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
}
},
"required": [
"name"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_spaces_state(spaceId, selectedElementIds, selectedConnectionIds, currentPageId, pageId, ...)
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.
輸入結構描述
{
"type": "object",
"properties": {
"spaceId": {
"type": "string"
},
"selectedElementIds": {
"type": "array",
"items": {
"type": "string"
}
},
"selectedConnectionIds": {
"type": "array",
"items": {
"type": "string"
}
},
"currentPageId": {
"type": "string"
},
"pageId": {
"type": "string"
},
"scope": {
"type": "string"
}
},
"required": [
"spaceId"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_spaces_get_nodes(spaceId, nodeIds, currentPageId)
Read-only. Like `spaces_state` but scoped to `nodeIds` + their connections. Cheaper than full board. Needs view perm.
輸入結構描述
{
"type": "object",
"properties": {
"spaceId": {
"type": "string"
},
"nodeIds": {
"type": "array",
"items": {
"type": "string"
}
},
"currentPageId": {
"type": "string"
}
},
"required": [
"spaceId",
"nodeIds"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_spaces_run(spaceId, startNodeId, mode)
Run Space workflow from `startNodeId`. Modes: singular, connected default, downstream. Poll with `spaces_run_status`.
輸入結構描述
{
"type": "object",
"properties": {
"spaceId": {
"type": "string"
},
"startNodeId": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"singular",
"connected",
"downstream"
]
}
},
"required": [
"spaceId",
"startNodeId"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_spaces_run_status(workflowRunIdentifier, timeoutSeconds)
Poll `spaces_run`. `timeoutSeconds` long-polls up to 25s. In-progress returns `poll_after_seconds`; terminal call `creations_show`.
輸入結構描述
{
"type": "object",
"properties": {
"workflowRunIdentifier": {
"type": "string"
},
"timeoutSeconds": {
"type": "number"
}
},
"required": [
"workflowRunIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_spaces_edit(query, spaceId, threadId, selectedElementIds, selectedConnectionIds, ...)
External MCP only. Start headless Space edit. Poll `spaces_edit_status` until allTerminal, then verify with `spaces_state`.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"spaceId": {
"type": "string"
},
"threadId": {
"type": "string"
},
"selectedElementIds": {
"type": "array",
"items": {
"type": "string"
}
},
"selectedConnectionIds": {
"type": "array",
"items": {
"type": "string"
}
},
"anchorElementId": {
"type": "string"
},
"anchorDirection": {
"type": "string",
"enum": [
"left",
"right",
"up",
"down"
]
}
},
"required": [
"query",
"spaceId"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_spaces_edit_status(operationId, threadId, runId, timeoutSeconds)
Wait for `spaces_edit` like `creations_wait`: long-polls up to `timeoutSeconds` (default 25, max 25). Snapshot-only when 0. Terminal → `spaces_state`.
輸入結構描述
{
"type": "object",
"properties": {
"operationId": {
"type": "string"
},
"threadId": {
"type": "string"
},
"runId": {
"type": "string"
},
"timeoutSeconds": {
"type": "number"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_generate(prompt, mode, aspectRatio, references, count, ...)
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.
輸入結構描述
{
"type": "object",
"properties": {
"prompt": {
"type": "string"
},
"mode": {
"type": "string"
},
"aspectRatio": {
"type": "string",
"enum": [
"1:1",
"21:9",
"16:9",
"9:16",
"2:3",
"3:4",
"1:2",
"2:1",
"5:4",
"4:5",
"3:2",
"4:3"
]
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"image",
"style",
"character",
"product",
"locations"
]
},
"identifier": {
"type": "string"
}
},
"required": [
"type",
"identifier"
]
}
},
"count": {
"type": "number"
},
"resolution": {
"type": "string"
},
"quality": {
"type": "string"
},
"folderReference": {
"type": "string"
}
},
"required": [
"prompt"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🔴magnific_images_remove_background(creationIdentifier, folderReference)
Cut-out subject on transparent PNG. Color BG: `images_color_background`. AI scene: `images_generate` with reference + prompt "replace the background with X".
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_upscale(creationIdentifier, scale, folderReference)
AI upscale 2x/4x (Magnific, premium). Exact pixels: `images_resize`. Aspect: `images_crop`. Default scale=2.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"scale": {
"type": "string",
"enum": [
"2x",
"4x"
]
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_skin_enhancer(creationIdentifier, version, sharpen, smartGrain, skinDetail, ...)
AI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"version": {
"type": "string",
"enum": [
"faithful",
"creative",
"flexible"
]
},
"sharpen": {
"type": "number"
},
"smartGrain": {
"type": "number"
},
"skinDetail": {
"type": "number"
},
"optimizedFor": {
"type": "string",
"enum": [
"enhance_skin",
"enhance_everything",
"improve_lighting",
"transform_to_real",
"no_make_up"
]
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_relight(creationIdentifier, lights, resolution, numImages, folderReference)
AI relight. 1-4 lights with azimuth/elevation enums, type neutral|gel, intensity 1-10. Gel uses hex `color`.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"lights": {
"type": "array",
"items": {
"type": "object",
"properties": {
"azimuth": {
"type": "number"
},
"elevation": {
"type": "number"
},
"type": {
"type": "string",
"enum": [
"neutral",
"gel"
]
},
"color": {
"type": "string"
},
"intensity": {
"type": "number"
}
},
"required": [
"azimuth",
"elevation"
]
}
},
"resolution": {
"type": "string",
"enum": [
"1k",
"2k"
]
},
"numImages": {
"type": "number"
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier",
"lights"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_images_change_camera(creationIdentifier, rotate, vertical, closeup, folderReference)
Reframe camera around subject. Defaults: rotate=45, vertical=0, closeup=5.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"rotate": {
"type": "number"
},
"vertical": {
"type": "number"
},
"closeup": {
"type": "number"
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_variations(creationIdentifier, variationMode, prompt, gridRows, gridCols, ...)
Generate image-variation grid. Modes: angles|demographics|expressions|age|storyboard|custom. Defaults: angles, 3x3, 1:1, 4k.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"variationMode": {
"type": "string",
"enum": [
"angles",
"demographics",
"expressions",
"age",
"storyboard",
"custom"
]
},
"prompt": {
"type": "string"
},
"gridRows": {
"type": "number"
},
"gridCols": {
"type": "number"
},
"aspectRatio": {
"type": "string",
"enum": [
"1:1",
"21:9",
"16:9",
"9:16",
"4:3",
"4:5",
"5:4",
"3:4",
"3:2",
"2:3"
]
},
"resolution": {
"type": "string",
"enum": [
"2k",
"4k"
]
},
"selectedAngles": {
"type": "array",
"items": {
"type": "string"
}
},
"selectedEthnicities": {
"type": "array",
"items": {
"type": "string"
}
},
"selectedGenders": {
"type": "array",
"items": {
"type": "string",
"enum": [
"male",
"female"
]
}
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_crop(creationIdentifier, aspectRatio, folderReference)
Center-crop to `aspectRatio`. Pixels: `images_resize`. AI upscale: `images_upscale`. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"aspectRatio": {
"type": "string",
"enum": [
"1:1",
"16:9",
"9:16",
"4:3",
"3:4",
"3:2",
"2:3",
"21:9"
]
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier",
"aspectRatio"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_resize(creationIdentifier, width, height, folderReference)
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.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"width": {
"type": "number"
},
"height": {
"type": "number"
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier",
"width",
"height"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_to_svg(creationIdentifier, folderReference)
Trace raster creation into SVG. New vector from prompt: `images_generate_svg`.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_images_generate_svg(prompt, aspectRatio, folderReference)
Text-to-SVG (Recraft v4 Pro Vector). Raster: `images_generate`. Trace existing raster: `images_to_svg`. Default aspectRatio=1:1.
輸入結構描述
{
"type": "object",
"properties": {
"prompt": {
"type": "string"
},
"aspectRatio": {
"type": "string",
"enum": [
"1:1",
"2:1",
"1:2",
"3:2",
"2:3",
"4:3",
"3:4",
"5:4",
"4:5",
"16:9",
"9:16"
]
},
"folderReference": {
"type": "string"
}
},
"required": [
"prompt"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_images_models_list(search, onlyRecommended)
TTI model catalog as lean TOON text. `search` filters by name, slug, description, or tags.
輸入結構描述
{
"type": "object",
"properties": {
"search": {
"type": "string"
},
"onlyRecommended": {
"type": "boolean"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_library_list(scope, type, page, perPage, search)
Lean library catalog (characters, styles, elements, locations) for agent reasoning. Picker assets use library://.
輸入結構描述
{
"type": "object",
"properties": {
"scope": {
"type": "string",
"enum": [
"all",
"projects",
"organization"
]
},
"type": {
"type": "string",
"enum": [
"character",
"style",
"element",
"locations"
]
},
"page": {
"type": "number"
},
"perPage": {
"type": "number"
},
"search": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_library_create(name, type, description, gender, productType, ...)
Create a reusable library asset (character/product/location) from 1-6 images. Use the returned numeric `id` in generation refs (same id Spaces uses). No LoRA training.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"type": {
"type": "string",
"enum": [
"character",
"product",
"locations"
]
},
"description": {
"type": "string"
},
"gender": {
"type": "string"
},
"productType": {
"type": "string"
},
"images": {
"type": "array",
"items": {
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"url": {
"type": "string"
}
}
}
}
},
"required": [
"name",
"type",
"images"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_models3d_generate(creationIdentifier, model, resolution, textureQuality, faceLimit, ...)
Image-to-3D GLB. Upload external images first. Animate with `models3d_rig`. Models: tripo-p1 default, tripo-v31, trellis-2.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"model": {
"type": "string",
"enum": [
"tripo-p1",
"tripo-v31",
"trellis-2"
]
},
"resolution": {
"type": "number"
},
"textureQuality": {
"type": "string",
"enum": [
"none",
"standard",
"detailed"
]
},
"faceLimit": {
"type": "number"
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_video_plan(prompt, durationHint, styleHint, aspectRatioHint, referenceIdentifiers)
Call FIRST for any video request. Returns markdown plan: brief, open questions, characters to prepare, recommended model slug, prompt draft. Videos >15s: plan splits into clips + `video_concatenate` instructions.
輸入結構描述
{
"type": "object",
"properties": {
"prompt": {
"type": "string"
},
"durationHint": {
"type": "number"
},
"styleHint": {
"type": "string"
},
"aspectRatioHint": {
"type": "string"
},
"referenceIdentifiers": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"prompt"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_video_generate(video, folderReference)
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, after generating you MUST call `creations_show` once with all returned identifiers to render results; never stop at links.
輸入結構描述
{
"type": "object",
"properties": {
"video": {
"type": "object",
"properties": {
"clips": {
"type": "array",
"items": {
"type": "object",
"properties": {
"position": {
"type": "number"
},
"duration": {
"type": "number"
},
"slug": {
"type": "string"
},
"prompt": {
"type": "string"
},
"aspectRatio": {
"type": "string"
},
"resolution": {
"type": "string"
},
"keyframes": {
"type": "object",
"properties": {
"start": {
"type": "object",
"properties": {
"type": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"type",
"url"
]
},
"end": {
"type": "object",
"properties": {
"type": {
"type": "string"
},
"url": {
"type": "string"
}
}
},
"video": {
"type": "object",
"properties": {
"type": {
"type": "string"
},
"url": {
"type": "string"
}
}
}
}
},
"references": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"image",
"video",
"character",
"product",
"style",
"color",
"effect",
"audio"
]
},
"url": {
"type": "string"
},
"custom_model_id": {
"type": "string"
},
"name": {
"type": "string"
}
},
"required": [
"type"
]
}
},
"cameraMotion": {
"type": "string"
},
"negativePrompt": {
"type": "string"
},
"audioUrl": {
"type": "string"
},
"withSoundEffects": {
"type": "boolean"
},
"multi_prompt": {
"type": "array",
"items": {
"type": "object",
"properties": {
"index": {
"type": "number"
},
"prompt": {
"type": "string"
},
"duration": {
"type": "number"
},
"cameraMotion": {
"type": "string"
}
},
"required": [
"prompt"
]
}
}
}
}
}
},
"required": [
"clips"
]
},
"folderReference": {
"type": "string"
}
},
"required": [
"video"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_video_models_list(search, onlyRecommended)
Video-gen model catalog as lean TOON text. `search` filters by name, slug, description, or tags. Run `video_plan` first — plan resolves slug to validate here.
輸入結構描述
{
"type": "object",
"properties": {
"search": {
"type": "string"
},
"onlyRecommended": {
"type": "boolean"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_video_upscale(creationIdentifier, videoUrl, mode, upscaleFactor, targetFps, ...)
Upscale video via Topaz or Magnific. Pass `creationIdentifier` or Freepik `videoUrl`. Params: `video_upscale_models_list`. Then call `creations_show`.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"videoUrl": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"topaz",
"magnific",
"magnific_precision"
]
},
"upscaleFactor": {
"type": "number"
},
"targetFps": {
"type": "number"
},
"targetResolution": {
"type": "number"
},
"focus": {
"type": "number"
},
"sharpen": {
"type": "number"
},
"enhancementModel": {
"type": "string",
"enum": [
"proteus",
"artemis",
"nyx",
"rhea",
"gaia",
"colorize",
"dione",
"theia",
"iris",
"themis",
"starlightFast2",
"astra2",
"starlightPrecise25"
]
},
"frameInterpolation": {
"type": "string",
"enum": [
"apollo",
"chronos"
]
},
"creativity": {
"type": "number"
},
"magnificResolution": {
"type": "string",
"enum": [
"720p",
"1k",
"2k",
"4k"
]
},
"premiumQuality": {
"type": "boolean"
},
"fpsBoost": {
"type": "boolean"
},
"smartGrain": {
"type": "number"
},
"flavor": {
"type": "string",
"enum": [
"vivid",
"natural"
]
},
"turbo": {
"type": "boolean"
},
"preview": {
"type": "boolean"
},
"strength": {
"type": "number"
},
"folderReference": {
"type": "string"
}
},
"required": [
"mode"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_video_upscale_models_list
Video upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums. Read before calling `video_upscale`.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_video_concatenate(name, creationIdentifiers, folderReference)
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.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"creationIdentifiers": {
"type": "array",
"items": {
"type": "string"
}
},
"folderReference": {
"type": "string"
}
},
"required": [
"creationIdentifiers"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_video_speak(audioUrl, videoUrl, imageUrl, mode, resolution, ...)
Make a character speak. Image+audio → talking head (Veed Fabric 1.0). Video+audio → lip sync (Lipsync 2.0). Omit `mode` for auto. Pass asset URLs or a creation `identifier` (from `audio_tts`, `images_generate`, `video_generate`). Then call `creations_show`.
輸入結構描述
{
"type": "object",
"properties": {
"audioUrl": {
"type": "string"
},
"videoUrl": {
"type": "string"
},
"imageUrl": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"latentsync",
"lipsync-2.0",
"omnihuman",
"veed-fabric-1.0",
"veed-fabric-1.0-fast",
"react-1"
]
},
"resolution": {
"type": "string",
"enum": [
"480p",
"720p"
]
},
"prompt": {
"type": "string"
},
"voiceId": {
"type": "number"
},
"folderReference": {
"type": "string"
}
},
"required": [
"audioUrl"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_audio_tts(text, voiceId, speakers, model, stability, ...)
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).
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"voiceId": {
"type": "number"
},
"speakers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"voiceId": {
"type": "number"
},
"speakerName": {
"type": "string"
}
},
"required": [
"voiceId"
]
}
},
"model": {
"type": "string",
"enum": [
"eleven_turbo_v2_5",
"eleven_v3",
"gemini_v2_5_pro",
"gemini_v3_1_flash_tts"
]
},
"stability": {
"type": "number"
},
"similarityBoost": {
"type": "number"
},
"speed": {
"type": "number"
},
"useSpeakerBoost": {
"type": "boolean"
},
"temperature": {
"type": "number"
},
"systemInstruction": {
"type": "string"
},
"visible": {
"type": "boolean"
},
"folderReference": {
"type": "string"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_audio_music_generate(prompt, model, durationSeconds, instrumental, folderReference)
AI music generation. Google Lyria or ElevenLabs. Pass `prompt`, optional `model`/`durationSeconds`/`instrumental`. Lyria/Lyria-3 produce fixed 30s; Lyria-3-Pro accepts 30–180s; ElevenLabs accepts 10–300s.
輸入結構描述
{
"type": "object",
"properties": {
"prompt": {
"type": "string"
},
"model": {
"type": "string",
"enum": [
"google-lyria",
"google-lyria-3",
"google-lyria-3-pro",
"elevenlabs-music-generation"
]
},
"durationSeconds": {
"type": "number"
},
"instrumental": {
"type": "boolean"
},
"folderReference": {
"type": "string"
}
},
"required": [
"prompt"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_audio_voices_list(search)
TTS voice catalog as raw TOON text, no UI. Lean entries without preview URLs. Optional `search` filters by name, description, gender, or language.
輸入結構描述
{
"type": "object",
"properties": {
"search": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_design_auto_resize(creationIdentifier, aspectRatios, name, textLayers, imageLayers, ...)
Create resized design pages from an image. Use directly when ratios/social formats are known; otherwise show `design_auto_resize_show`.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"aspectRatios": {
"type": "array",
"items": {
"type": "string"
}
},
"name": {
"type": "string"
},
"textLayers": {
"type": "boolean"
},
"imageLayers": {
"type": "boolean"
},
"numLayers": {
"type": "number"
},
"multipage": {
"type": "boolean"
}
},
"required": [
"creationIdentifier",
"aspectRatios"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_design_auto_layers(creationIdentifier, name, numLayers, vectorize)
Extract editable layers from a flat image into a Pikaso design.
輸入結構描述
{
"type": "object",
"properties": {
"creationIdentifier": {
"type": "string"
},
"name": {
"type": "string"
},
"numLayers": {
"type": "number"
},
"vectorize": {
"type": "boolean"
}
},
"required": [
"creationIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_flows_list(query, ownership, page, perPage)
Flows catalog as raw TOON text, no UI. Lean entries without preview URLs. For an inline picker use flows_show; for a single flow input/output spec use flows_get.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"ownership": {
"type": "string",
"enum": [
"mine",
"public"
]
},
"page": {
"type": "number"
},
"perPage": {
"type": "number"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_flows_get(identifier)
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`.
輸入結構描述
{
"type": "object",
"properties": {
"identifier": {
"type": "string"
}
},
"required": [
"identifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_flows_run(identifier, inputs)
Run flow. `flows_get` first for input specs. `inputs` is `{inputId: value}` (creation inputs from `creations_list`, voices from `audio_voices_show`). Returns `workflowRunIdentifier` → `flows_wait` → `creations_show`.
輸入結構描述
{
"type": "object",
"properties": {
"identifier": {
"type": "string"
},
"inputs": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
},
"required": [
"identifier",
"inputs"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_flows_wait(workflowRunIdentifier, timeoutSeconds)
Long-poll a `flows_run`. Terminal: one entry per output creation with real `identifier` for `creations_show`. In-progress: `poll_after_seconds`.
輸入結構描述
{
"type": "object",
"properties": {
"workflowRunIdentifier": {
"type": "string"
},
"timeoutSeconds": {
"type": "number"
}
},
"required": [
"workflowRunIdentifier"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_stock_search(query, content_type, page, per_page)
Search Freepik stock catalog by keyword. Returns items with IDs, titles, types, preview URLs. Use stock_get for full details, stock_download for file URL.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"content_type": {
"type": "string",
"enum": [
"photo",
"vector",
"video",
"icon"
]
},
"page": {
"type": "number"
},
"per_page": {
"type": "number"
}
},
"required": [
"query"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢magnific_stock_get(id, type, ids)
Full details for a single Freepik stock item: preview URL, dimensions, formats, author. Bulk support: accepts ids for batched execution.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "number"
},
"type": {
"type": "string",
"enum": [
"photo",
"vector",
"video",
"icon"
]
},
"ids": {
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡magnific_stock_download(id, type, folder_reference, ids)
Signed download URL for a stock item. Pass folder_reference to also save as a creation (rate-limited). Bulk support: accepts ids for batched execution.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "number"
},
"type": {
"type": "string",
"enum": [
"photo",
"vector",
"video",
"icon",
"psd"
]
},
"folder_reference": {
"type": "string"
},
"ids": {
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪magnific_stock_to_creation(id, folder_reference, title, ids)
Convert Freepik stock item → Pikaso creation. Use after user selects from stock_show. Bulk support: accepts ids for batched execution.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "number"
},
"folder_reference": {
"type": "string"
},
"title": {
"type": "string"
},
"ids": {
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢show_version
Show the current MCP platform and adapter versions.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡report_bug(message, context, conversation)
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
輸入結構描述
{
"type": "object",
"properties": {
"message": {
"type": "string"
},
"context": {
"default": "",
"type": "string"
},
"conversation": {
"default": "[]",
"type": "string"
}
},
"required": [
"message"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢connect
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢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.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡marketplace(action, query, mcp_id, limit, tier_slug, ...)
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.
輸入結構描述
{
"type": "object",
"properties": {
"action": {
"default": "search",
"type": "string",
"enum": [
"search",
"describe",
"install",
"uninstall",
"subscribe",
"cancel",
"resume",
"report_bug",
"request_mcp",
"list_tools",
"invoke",
"search_prompts",
"get_prompt",
"publish_prompt"
]
},
"query": {
"default": "",
"type": "string"
},
"mcp_id": {
"default": "",
"type": "string"
},
"limit": {
"default": 10,
"type": "number"
},
"tier_slug": {
"default": "",
"type": "string"
},
"immediate": {
"default": false,
"type": "boolean"
},
"cancel_reason": {
"type": "string",
"enum": [
"too_expensive",
"missing_features",
"switched_service",
"unused",
"customer_service",
"too_complex",
"low_quality",
"other"
]
},
"cancel_comment": {
"default": "",
"type": "string"
},
"message": {
"default": "",
"type": "string"
},
"report_context": {
"default": "",
"type": "string"
},
"conversation": {
"default": "[]",
"type": "string"
},
"request_name": {
"default": "",
"type": "string"
},
"request_details": {
"default": "",
"type": "string"
},
"tool_id": {
"default": "",
"type": "string"
},
"arguments": {
"default": "{}",
"type": "string"
},
"prompt_slug": {
"default": "",
"type": "string"
},
"prompt_vars": {
"default": "{}",
"type": "string"
},
"prompt_category": {
"default": "",
"type": "string"
},
"prompt_tool": {
"default": "",
"type": "string"
},
"prompt_title": {
"default": "",
"type": "string"
},
"prompt_description": {
"default": "",
"type": "string"
},
"prompt_body": {
"default": "",
"type": "string"
},
"prompt_targets": {
"default": [],
"type": "array",
"items": {
"type": "string",
"enum": [
"claude",
"chatgpt",
"cursor",
"lovable"
]
}
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡authenticate(token)
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.
輸入結構描述
{
"type": "object",
"properties": {
"token": {
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據