原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Magnific

作者:mcp-dir版本 0.1.0i★ 0i在云端运行官方网站 ↗
注册名称io.github.mcp-dir/magnific-mcp

安装方法

What it does

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

  • Connects 在云端运行
  • Account or key No key needed
  • Category 设计、图片与音频

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

作者:pbakaus★ 112,5441 个 skill

Skill · 操作手册

diagram-design

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

作者:cathrynlavery★ 68,0691 个 skill

Skill · 操作手册

frontend-slides

Create beautiful slides on the web using a coding agent's frontend skills

作者:zarazhangrui★ 32,5141 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度7/1230 天内有发布或代码更新得满分
仍在响应8/8上次检查时云端端点有响应
使用分15/100

质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 Magnific。按照 https://mcp.popnx.com/i/mcp-dir-magnific-mcp.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 5/5 项检查 · 你的提问会经过开发者的服务器(api.mcp.ai) · ✓ 命令已检查 2026年11月13日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称Magnific
    Remote MCP server URL · 地址https://api.mcp.ai/p_magnific

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsMagnific

  4. 试一试

    用 Magnific 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Magnific,或回答中出现 Magnific 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称Magnific
    Connection · 地址https://api.mcp.ai/p_magnific
  3. 在聊天中选择 Magnific

    开启新聊天,输入前先从插件列表中选择 Magnific

  4. 试一试

    用 Magnific 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 Magnific,或回答中出现 Magnific 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user magnific https://api.mcp.ai/p_magnific
  3. 在 Claude Code 中输入 /mcp

    应能看到 Magnific 在列表中并显示已连接

  4. 试一试

    用 Magnific 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 Magnific,或回答中出现 Magnific 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Magnific 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 Magnific,或回答中出现 Magnific 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Magnific 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 Magnific,或回答中出现 Magnific 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://api.mcp.ai/p_magnific

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Magnific 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

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

Cursor (~/.cursor/mcp.json)

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

VS Code (mcp.json)

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

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在云端运行
传输方式
streamable-http
最新版本i
0.1.0
发布到注册中心i
2026年8月21日
代码最后更新i
2026年8月31日
最近检查
2026年11月15日
作者
mcp-dir
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月15日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • magnific_account_balance

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

  • 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.

  • magnific_creations_get

    Single creation complete data — metadata + URLs (`url` full-res, `previewUrl` ~1024px, `thumbnailUrl` ~400px).

  • 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.

  • magnific_creations_list

    Filterable gallery widget (image/video/audio). Use instead of `creations_search` when user wants to browse their library.

  • magnific_creations_request_upload

    Step 1 for local/user files: get presigned PUT URL(s). Upload bytes outside MCP, then call `creations_finalize_upload`.

  • magnific_creations_finalize_upload

    Step 2 after PUT from `creations_request_upload`: convert temp path(s) to creations. Images <=25MB, videos <=200MB.

  • magnific_creations_upload_image

    Upload public image URL in one step. For local/user files use `creations_request_upload` then `creations_finalize_upload`.

  • 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`.

  • magnific_creations_move

    Move creations into `targetFolderReference`. Identifiers from `images_generate`/`creations_search`. Foreign identifier → abort. Target folder must belong to user.

  • magnific_creations_like

    Toggle heart/favorite reaction on a user-owned creation.

  • magnific_creations_comment

    Add a comment (or reply) to a user-owned creation.

  • magnific_folders_list

    List folders/projects as raw TOON text. No params=top level; `onlyProjects`=projects; `parentReference`=children. Refs work with creations/folder tools.

  • magnific_folders_get

    Fetch folder metadata by `reference`. Use before `creations_search` (`from=folder`). Foreign refs error.

  • magnific_folders_create

    Create folder/project. No `parentReference`: workspace root. `type` defaults: project at root, folder when nested.

  • magnific_folders_rename

    Rename a folder by `reference`.

  • magnific_folders_delete

    Move a folder and its files to trash.

  • magnific_project_report

    English markdown status report for a project/folder. Last 7 days default, max 30.

  • 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`.

  • magnific_spaces_create

    Create empty Space. Share `space.webUrl`; only call `spaces_show` when inline preview is requested.

  • 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.

  • magnific_spaces_get_nodes

    Read-only. Like `spaces_state` but scoped to `nodeIds` + their connections. Cheaper than full board. Needs view perm.

  • magnific_spaces_run

    Run Space workflow from `startNodeId`. Modes: singular, connected default, downstream. Poll with `spaces_run_status`.

  • magnific_spaces_run_status

    Poll `spaces_run`. `timeoutSeconds` long-polls up to 25s. In-progress returns `poll_after_seconds`; terminal call `creations_show`.

  • magnific_spaces_edit

    External MCP only. Start headless Space edit. Poll `spaces_edit_status` until allTerminal, then verify with `spaces_state`.

  • 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`.

  • 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.

  • 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".

  • magnific_images_upscale

    AI upscale 2x/4x (Magnific, premium). Exact pixels: `images_resize`. Aspect: `images_crop`. Default scale=2.

  • magnific_images_skin_enhancer

    AI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0.

  • magnific_images_relight

    AI relight. 1-4 lights with azimuth/elevation enums, type neutral|gel, intensity 1-10. Gel uses hex `color`.

  • magnific_images_change_camera

    Reframe camera around subject. Defaults: rotate=45, vertical=0, closeup=5.

  • magnific_images_variations

    Generate image-variation grid. Modes: angles|demographics|expressions|age|storyboard|custom. Defaults: angles, 3x3, 1:1, 4k.

  • 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.

  • 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.

  • magnific_images_to_svg

    Trace raster creation into SVG. New vector from prompt: `images_generate_svg`.

  • magnific_images_generate_svg

    Text-to-SVG (Recraft v4 Pro Vector). Raster: `images_generate`. Trace existing raster: `images_to_svg`. Default aspectRatio=1:1.

  • magnific_images_models_list

    TTI model catalog as lean TOON text. `search` filters by name, slug, description, or tags.

  • magnific_library_list

    Lean library catalog (characters, styles, elements, locations) for agent reasoning. Picker assets use library://.

  • 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.

  • magnific_models3d_generate

    Image-to-3D GLB. Upload external images first. Animate with `models3d_rig`. Models: tripo-p1 default, tripo-v31, trellis-2.

  • 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.

  • 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 re

  • 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.

  • magnific_video_upscale

    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

    Video upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums. Read before calling `video_upscale`.

  • 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.

  • 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`.

  • 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).

  • 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.

  • 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.

  • 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`.

  • magnific_design_auto_layers

    Extract editable layers from a flat image into a Pikaso design.

  • 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.

  • 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`.

  • 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`.

  • 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`.

  • 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.

  • magnific_stock_get

    Full details for a single Freepik stock item: preview URL, dimensions, formats, author. Bulk support: accepts ids for batched execution.

  • 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.

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 mcp-dir 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3个月前

  • ✓ 通过

    有许可证

    使用 MIT

  • ✓ 通过

    端点有响应

    在 103 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 60 个工具描述,未发现针对 AI 的隐藏指令

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/mcp-dir-magnific-mcp.svg)](https://mcp.popnx.com/en/servers/mcp-dir-magnific-mcp)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“设计、图片与音频”中的其他服务器比较i

  • 星标数多于此分类中其他 3261 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 3261 个服务器的 20% 更新
  • 基础检查结果等于或优于此分类中其他 3261 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Magnific 安全吗?

它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于3个月前,最新版本(0.1.0)于3个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

作者:pascalorg广泛使用↓ 1037/周★ 2.6万 整个仓库的星标昨天更新

电脑或云端✓ 服务方 · pascal.app

draw.io

Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.

作者:jgraph广泛使用★ 5848前天更新

在云端运行✓ 服务方 · draw.ioPopNx 团队已实际试用

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

作者:figma广泛使用★ 220713个月前更新

在云端运行✓ 服务方 · mcp.figma.com
与相似项目对比
本项
Magnific
HyperFrames by HeyGenPascal 3D Editordraw.ioFigma MCP ServerRemocn: Remotion MCP server
运行位置在云端运行,无需安装在云端运行,无需安装云端或安装在电脑上都可以在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否是否
基础检查5/54/45/54/44/44/4
许可证MITApache-2.0MITApache-2.0–MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Magnific

Magnific para Claude, ChatGPT e agentes de IA

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


Instalar em 1 clique

Claude (Web e Desktop)

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):

➕ Abrir no Claude e conectar

Manual (se o deeplink não abrir): claude.ai/customize/connectors → + → Adicionar conector personalizado → cole Nome Magnific e URL https://api.mcp.ai/p_magnific.

Cursor

➕ Instalar Magnific no Cursor

VS Code (Copilot Chat)

➕ Instalar Magnific no VS Code

ChatGPT, Manus, OpenClaw e mais 40+ clientes

Funciona em qualquer cliente MCP que suporte MCP over HTTP. A URL do servidor é sempre:

https://api.mcp.ai/p_magnific

Detalhes por cliente: INSTALL.md.


Exemplos de uso

Faça upscale dessa imagem no Magnific

Liste minhas criações recentes no Magnific Gere uma variação dessa imagem no Magnific


61 ferramentas disponíveis

ToolDescrição
magnific_account_balanceUser plan + credits. Check before paid generations. Returns plan.{tier,productName,isUnlimitedMode}, credits.{available,totalPlan,spent,hasExtraCredits}. No history.
magnific_creations_waitLong-poll 1..8 creations until terminal or timeoutSeconds (default 25, max 25).
magnific_creations_getSingle creation complete data — metadata + URLs (url full-res, previewUrl ~1024px, thumbnailUrl ~400px).
magnific_creations_searchSearch user creations as raw TOON text.
magnific_creations_listFilterable gallery widget (image/video/audio).
magnific_creations_request_uploadStep 1 for local/user files: get presigned PUT URL(s).
magnific_creations_finalize_uploadStep 2 after PUT from creations_request_upload: convert temp path(s) to creations.
magnific_creations_upload_imageUpload public image URL in one step.
magnific_creations_upload_fileImport a file the user attached in the host (e.g.
magnific_creations_moveMove creations into targetFolderReference.
magnific_creations_likeToggle heart/favorite reaction on a user-owned creation.
magnific_creations_commentAdd a comment (or reply) to a user-owned creation.
magnific_folders_listList folders/projects as raw TOON text.
magnific_folders_getFetch folder metadata by reference.
magnific_folders_createCreate folder/project. No parentReference: workspace root. type defaults: project at root, folder when nested.
magnific_folders_renameRename a folder by reference.
magnific_folders_deleteMove a folder and its files to trash.
magnific_project_reportEnglish markdown status report for a project/folder.
magnific_spaces_listLean spaces catalog as raw TOON text.
magnific_spaces_createCreate empty Space. Share space.webUrl; only call spaces_show when inline preview is requested.
magnific_spaces_stateRead-only board context, raw TOON.
magnific_spaces_get_nodesRead-only. Like spaces_state but scoped to nodeIds + their connections. Cheaper than full board. Needs view perm.
magnific_spaces_runRun Space workflow from startNodeId.
magnific_spaces_run_statusPoll spaces_run. timeoutSeconds long-polls up to 25s. In-progress returns poll_after_seconds; terminal call creations_show.
magnific_spaces_editExternal MCP only. Start headless Space edit. Poll spaces_edit_status until allTerminal, then verify with spaces_state.
magnific_spaces_edit_statusWait for spaces_edit like creations_wait: long-polls up to timeoutSeconds (default 25, max 25).
magnific_images_generateGenerate/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 w…
magnific_images_remove_backgroundCut-out subject on transparent PNG.
magnific_images_upscaleAI upscale 2x/4x (Magnific, premium).
magnific_images_skin_enhancerAI skin enhancer. faithful preserves identity; creative reinterprets; flexible uses presets. Defaults: faithful, sharpen=0, smartGrain=0.
magnific_images_relightAI relight. 1-4 lights with azimuth/elevation enums, type neutralgel, intensity 1-10. Gel uses hex color.
magnific_images_change_cameraReframe camera around subject.
magnific_images_variationsGenerate image-variation grid.
magnific_images_cropCenter-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_resizeResize to exact pixels (no AI).
magnific_images_to_svgTrace raster creation into SVG.
magnific_images_generate_svgText-to-SVG (Recraft v4 Pro Vector).
magnific_images_models_listTTI model catalog as lean TOON text.
magnific_library_listLean library catalog (characters, styles, elements, locations) for agent reasoning.
magnific_library_createCreate a reusable library asset (character/product/location) from 1-6 images.
magnific_models3d_generateImage-to-3D GLB. Upload external images first. Animate with models3d_rig. Models: tripo-p1 default, tripo-v31, trellis-2.
magnific_video_planCall FIRST for any video request.
magnific_video_generateGenerate 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 f…
magnific_video_models_listVideo-gen model catalog as lean TOON text.
magnific_video_upscaleUpscale video via Topaz or Magnific.
magnific_video_upscale_models_listVideo upscale mode catalog as raw TOON text (topaz, magnific, magnific_precision) with required/optional params, ranges and enums.
magnific_video_concatenateConcatenate completed video creations into one MP4.
magnific_video_speakMake 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…
magnific_audio_ttsTTS 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_music_generateAI 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_voices_listTTS voice catalog as raw TOON text, no UI.
magnific_design_auto_resizeCreate resized design pages from an image.
magnific_design_auto_layersExtract editable layers from a flat image into a Pikaso design.
magnific_flows_listFlows catalog as raw TOON text, no UI.
magnific_flows_getFlow input/output spec as raw TOON text.
magnific_flows_runRun 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_waitLong-poll a flows_run. Terminal: one entry per output creation with real identifier for creations_show. In-progress: poll_after_seconds.
magnific_stock_searchSearch Freepik stock catalog by keyword.
magnific_stock_getFull details for a single Freepik stock item: preview URL, dimensions, formats, author.
magnific_stock_downloadSigned download URL for a stock item.

Detalhe de cada tool: docs/ferramentas.md


Preços

Grátis.


Privacidade & LGPD

  • 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.

Perguntas frequentes

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.


Suporte


Licença

MIT — veja LICENSE. O servidor MCP em api.mcp.ai/p_magnific é proprietário (hosted); este repositório (manifestos, docs, skills) é MIT.