nakkaş 在土耳其语（古语）中意为画家/艺术家。
"make a neon terminal logo with animated binary digits"
→ AI constructs JSON config
→ nakkas renders to animated SVG
→ clean animated SVG output一个工具，无限设计。 render_svg 接收 JSON 配置。AI 填充所有内容。
AI 原生模式。 每个字段都有 .describe() 注解，以便模型知道该做什么。
纯声明式 SVG。 CSS @keyframes + SMIL 动画，无需 JavaScript。
零外部依赖。 无云 API，无 API 密钥。本地运行。
Related MCP server: inkscape_mcp
添加到您的配置文件中：
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"nakkas": {
"command": "npx",
"args": ["-y", "nakkas@latest"]
}
}
}claude mcp add nakkas npx nakkas@latest{
"mcpServers": {
"nakkas": {
"command": "npx",
"args": ["-y", "nakkas@latest"]
}
}
}git clone https://github.com/arikusi/nakkas
cd nakkas
npm install && npm run build
# Use dist/index.js as the command询问您的 AI（在连接 Nakkas 的情况下）：
"制作一个动态 SVG：深色终端框架 (800×200)，发光的青色文字 'NAKKAS'，霓虹发光滤镜，加载时淡入。"
"创建一个加载旋转器：一个带有绘制描边动画的圆圈，每 1.5 秒循环一次。"
"数据可视化：动态柱状图，5 个柱子，每个柱子交错延迟淡入，渐变填充。"
"个人资料徽章 (400×120)：蓝到紫渐变，白色用户名文字，投影，细微的脉冲动画。"
Nakkas 提供三个工具：
工具 | 用途 |
| 接收 SVGConfig JSON，返回 SVG 字符串 + 设计分析警告 |
| 接收渲染内容，返回用于视觉检查的 PNG 图像 |
| 接收渲染内容，保存为 SVG（文本）或 PNG（栅格）到磁盘 |
推荐工作流：渲染 → 预览 → 迭代 → 保存。save 工具与 render_svg 分开，旨在鼓励在保存前进行预览和优化。
save 工具{ "content": "<svg ...>...</svg>", "outputPath": "./design.svg", "format": "auto" }格式：auto（根据扩展名推断）、svg（文本文件）、png（先渲染为栅格）。如果文件已存在，将附加一个数字计数器以防止覆盖。返回实际保存的路径。
render_svg 工具输入： SVGConfig JSON 对象
输出： 完整的 SVG XML 字符串以及可选的设计分析说明
渲染后，响应可能包含关于常见问题的设计警告，例如并发动画过多、缺少 transformBox 或组级缩放变换。
{
canvas: {
width: number | string, // e.g. 800 or "100%"
height: number | string,
viewBox?: string, // "0 0 800 400"
background?: string // hex "#111111" or "transparent"
},
defs?: {
gradients?: Gradient[], // linearGradient | radialGradient
filters?: Filter[], // preset or raw primitives
clipPaths?: ClipPath[],
masks?: Mask[],
symbols?: Symbol[],
paths?: { id, d }[] // for textPath elements
},
elements: Element[], // shapes, text, groups, use instances
animations?: CSSAnimation[] // CSS @keyframes definitions
}类型 | 必需字段 | 说明 |
|
|
|
|
|
|
|
| 独立的水平/垂直半径 |
|
| |
|
| 开放路径： |
|
| 自动闭合形状 |
|
| 完整的 SVG 路径命令 |
|
| 用于嵌入图像的 URL 或 |
|
| 字符串或 |
|
| 沿曲线排列的文本；路径定义在 |
|
| 应用于所有子元素的共享属性（不支持嵌套组） |
|
| 实例化符号或通过 |
|
| 在完整圆周上放置 N 个副本 |
|
| 沿圆弧放置 N 个副本 |
|
| 在 M x N 网格中放置副本 |
|
| 在种子随机位置散布 N 个副本 |
|
| 沿折线均匀分布 N 个副本 |
|
| 数学曲线： |
{
id?: string, // required for filter/gradient/clip references
cssClass?: string, // matches CSS animation names
fill?: string, // "#rrggbb" | "none" | "url(#gradId)"
stroke?: string,
strokeWidth?: number,
strokeDasharray?: string, // "10 5", use for draw-on animation
strokeDashoffset?: number,
opacity?: number, // 0–1
filter?: string, // "url(#filterId)"
clipPath?: string, // "url(#clipId)"
transform?: string, // "rotate(45)" "translate(100, 50)"
transformBox?: "fill-box" | "view-box" | "stroke-box", // set "fill-box" for CSS rotation
transformOrigin?: string, // "center", works with fill-box
smilAnimations?: SMILAnimation[]
}在 defs.filters 中定义后，可在任何元素上通过 filter: "url(#myId)" 引用：
{ "type": "preset", "id": "myGlow", "preset": "glow", "stdDeviation": 8, "color": "#ff00ff" }预设 | 关键参数 | 效果 |
|
| 柔和光晕 |
|
| 强光 |
|
| 高斯模糊 |
|
| 投影 |
|
| 湍流置换（动态） |
|
| 去色 |
| — | 暖棕褐色调 |
| — | 反转颜色 |
|
| 增强/降低饱和度 |
|
| 色相旋转 |
|
| RGB 通道分离，产生镜头畸变效果 |
|
| 胶片颗粒和纹理叠加 |
|
| 元素周围的彩色轮廓 |
|
| 元素内部阴影 |
|
| 3D 浮雕阴影效果 |
{
"animations": [{
"name": "pulse",
"duration": "2s",
"iterationCount": "infinite",
"direction": "alternate",
"keyframes": [
{ "offset": "from", "properties": { "opacity": "0.3", "transform": "scale(0.9)" } },
{ "offset": "to", "properties": { "opacity": "1", "transform": "scale(1.1)" } }
]
}],
"elements": [{
"type": "circle",
"cx": 100, "cy": 100, "r": 40,
"cssClass": "pulse",
"transformBox": "fill-box",
"transformOrigin": "center"
}]
}CSS 属性键：驼峰式 (strokeDashoffset) 或短横线式 (stroke-dashoffset)。两者均可。
可动画化的 CSS 属性：opacity, fill, stroke, transform, filter, clip-path, stroke-dasharray, stroke-dashoffset, font-size, letter-spacing 等。
三种 SMIL 类型，通过 smilAnimations: [] 在每个元素上内联定义：
{ "kind": "animate", "attributeName": "d", "from": "...", "to": "...", "dur": "2s" }
{ "kind": "animateTransform", "type": "rotate", "from": "0 100 100", "to": "360 100 100", "dur": "3s" }
{ "kind": "animateMotion", "path": "M 0 0 C ...", "dur": "4s", "rotate": "auto" }路径变形 (attributeName: "d")：from/to 路径必须具有相同的命令类型和数量。仅坐标可以不同。
系统字体无需加载即可在任何地方使用：Arial, Helvetica, Courier New, Georgia, Verdana, monospace, sans-serif, serif。
也接受自定义字体系列。当渲染环境中存在该字体（加载了字体的网页、设计工具等）时，它们可以正常工作。
上下文 | CSS @keyframes | SMIL | 外部字体 | 交互 (onclick) |
GitHub README | ✅ | ✅ | ❌ | ❌ |
网页 | ✅ | ✅ | ❌ | ❌ |
网页内联 SVG | ✅ | ✅ | ✅ | ✅ |
设计工具导出 | ✅ | ✅ | ✅ | — |
静态文件查看器 | ✅ | ✅ | 取决于环境 | 取决于环境 |
这意味着 MCP SDK 在到达处理程序之前拒绝了输入。这通常发生在第一次尝试时，重试即可解决。最常见的原因：
渐变类型拼写错误。 使用 "linearGradient" 或 "radialGradient"，而不是 "linear" 或 "radial"。这是最常见的错误。
关键帧偏移量作为字符串。 写入 0 或 100（数字）或 "from" / "to"。写入 "0%" 或 "100%" 将会失败。
命名颜色。 仅十六进制值有效："#ff0000"，而不是 "red"。也不支持 rgb()。
元素缺少 type。 每个元素对象都需要一个 type 字段。
如果您在构建 MCP 客户端集成时持续看到此错误，问题可能出在客户端序列化参数的方式上。有关已知序列化怪癖的背景信息，请参阅 anthropics/claude-code#29104。
预览工具在 t=0 时渲染静态快照。动画不会被捕获。您看到的是 SVG 在任何 CSS 或 SMIL 动画开始前的初始状态。
如果图像完全空白：
检查您的元素是否设置了 fill 或 stroke。在透明画布上没有填充的形状是不可见的。
检查坐标。在 800px 宽的画布上，位于 x: 2000 的元素在屏幕外。
如果使用 filter: "url(#myFilter)"，请确保 myFilter 已在 defs.filters 中定义。
GitHub README 通过 <img> 标签渲染 SVG，该标签会剥离 JavaScript，但保留 CSS 和 SMIL。如果您的动画在本地有效但在 GitHub 上无效：
避免使用 <script> 或事件处理程序 (onclick, onmouseover)。这些会被移除。
外部字体不会加载。请坚持使用系统字体：Arial, Courier New, Georgia, monospace, sans-serif。
字体 CSS @import 被阻止。如果需要特定字体，请使用带有系统回退的内联 <text>。
如果 render_svg 返回关于文件大小（超过 50kb）的警告，可能是参数化曲线或图案组生成了过多的元素。减少参数化曲线的 steps 或图案组的 count。一个 cols: 50, rows: 50 的网格组会产生 2500 个元素，这会迅速增加文件大小。
TypeScript + Node.js 18+
@modelcontextprotocol/sdk (MCP 服务器)
zod (模式验证和 AI 类型引导)
无外部 SVG 库，纯 XML 构建
Vitest (280 个测试)
MIT。由 arikusi 构建。
Render SVG content to a PNG image so the AI can visually inspect the output.
When to use:
render_svg already returns a preview image by default; call this tool to re-preview a stored artifact at a different width, or to preview SVG that did not come from render_svg
Stop iterating when the visual result matches the intent
Input: pass EITHER artifact (id from render_svg, e.g. "art-1" — preferred, no SVG resend) OR content (raw SVG string).
Behavior:
Returns a PNG image (base64) rendered from the SVG
Background is transparent by default
CSS animations and SMIL are rendered as a static snapshot (t=0) — motion is not captured
Width:
Omit width to use the SVG's own declared width/viewBox
Pass width to scale the output (useful for small SVGs that need a larger preview)
| Name | Required | Description | Default |
|---|---|---|---|
| width | No | Render width in pixels; defaults to SVG's own declared width | |
| format | No | Content format; auto-detected from content if omitted | |
| content | No | SVG string to render as PNG. Only needed when no artifact id exists. | |
| artifact | No | Artifact id returned by render_svg (e.g. "art-1"). Preferred over content. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the output is a PNG base64, background is transparent, animations are static snapshots, and width can be omitted or specified. It does not contradict any annotations (none provided). However, it does not explain the 'format' parameter's effect (e.g., when to use 'html') though schema covers it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with sections (When to use, Input, Behavior, Width), front-loaded with purpose, and every sentence adds value without unnecessary text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 optional parameters, no output schema, and no annotations, the description covers key behaviors and usage contexts. It does not explicitly state mutual exclusivity of artifact and content, but the 'pass EITHER' guidance implies it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% so baseline is 3. The description adds meaning by explaining that 'artifact' is preferred over 'content', width can be left to default, and content is only needed when no artifact id exists.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states clearly 'Render SVG content to a PNG image so the AI can visually inspect the output.' It distinguishes from sibling tool render_svg by noting that render_svg already returns a preview and this tool is for re-previewing or previewing external SVG.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'When to use' section explicitly tells when to use this tool vs render_svg, including re-previewing artifacts or previewing SVG from other sources. It also advises to stop iterating when visual result matches intent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Render animated SVG from JSON config. AI controls all design parameters.
Workflow: render_svg returns a PNG preview of the result plus an artifact id — critique the image, revise the config, render again. Iterate at least 3 times before finalizing. The SVG text stays on the server: pass the artifact id to save (and to preview for a different width). Add output:{svg:true} only if you actually need the SVG text in the conversation.
output options (response shape, not content): {"svg":false,"preview":true,"previewWidth":800,"minify":false,"frames":4} — all optional. minify:true collapses whitespace in the stored/saved SVG. frames:N (2-10) replaces the static preview with one filmstrip image sampling the CSS animations at N times — use it to verify motion (rotation direction, timing, easing) since a single preview only shows t=0. SMIL is not sampled.
Element types: rect, circle, ellipse, line, polyline, polygon, path, image, text, textPath, group, use, radial-group, arc-group, grid-group, scatter-group, path-group, parametric
Pattern groups (use for repetitive designs): radial-group (circular: cx, cy, radius, count), arc-group (arc: cx, cy, radius, count, startAngle, endAngle), grid-group (matrix: cols, rows, colSpacing, rowSpacing), scatter-group (random: width, height, count, seed), path-group (along polyline: waypoints, count). Each takes ONE "child" element.
Parametric curves (fn field): rose, heart, lissajous, spiral, star, superformula, epitrochoid, hypotrochoid, wave. Size via "scale" field. Server computes coordinates.
defs: gradients (linear/radial, SMIL animated stops), filters (presets: glow, neon, blur, drop-shadow, glitch, chromatic-aberration, noise, outline, inner-shadow, emboss + 5 more), clipPaths, masks, patterns (tile fills).
Animations: CSS @keyframes via animations array. Set cssClass on element matching animation name. For transforms add transformBox="fill-box" transformOrigin="center". SMIL via smilAnimations on elements (animate, animateTransform, animateMotion).
Critical format rules:
Gradient type must be "linearGradient" or "radialGradient" (not "linear"/"radial"). Each needs id, stops (array with offset 0-1, color).
Filter type must be "preset" with a "preset" field: {"type":"preset","id":"myGlow","preset":"glow","stdDeviation":8,"color":"#ff00ff"}
Keyframe offset: use "from"/"to" or percentage number 0-100 (not "0%"/"100%").
Gradient stop and filter colors: hex only (#rrggbb or #rrggbbaa). Element fill/stroke accept '#rrggbb', 'none', or 'url(#id)' (hex is safest).
Every element needs "type" field. circle needs r, rect needs width+height, path needs d.
Field names that differ from raw SVG:
text: string goes in "content" (not "text"): {"type":"text","x":100,"y":50,"content":"Hello","fontSize":24,"textAnchor":"middle"}
textPath: {"type":"textPath","pathId":"idFromDefsPaths","text":"..."} — here the field IS "text".
group: {"type":"group","children":[...]} — children are shapes/text/use only, no nested groups.
Pattern groups take ONE "child" element drawn at local origin (child uses cx=0/cy=0); set rotateChildren:false to keep text upright.
Output: Pure SVG XML. No JavaScript. CSS @keyframes + SMIL only.
| Name | Required | Description | Default |
|---|---|---|---|
| defs | No | ||
| canvas | Yes | ||
| output | No | ||
| elements | Yes | ||
| animations | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It transparently discloses that SVG text stays on the server (access via artifact id), describes output format (PNG preview + artifact id), explains field name differences from raw SVG, critical format rules, and the behavior of pattern groups and parametric curves. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured with sections (Workflow, output options, element types, pattern groups, etc.). Every sentence adds necessary detail given the complexity of SVG rendering. Slightly verbose but justified; could be tightened without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 params, nested objects, no output schema), the description covers all essential aspects: input structure, workflow, output format, edge cases (field name differences, format rules), and usage of defs and animations. It explains return values (PNG preview + artifact id) despite no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate fully. It provides extensive detail on each parameter group (canvas, elements, animations, output, defs) with examples, required fields, and format constraints (e.g., gradient type must be 'linearGradient', elements need 'type' field). This goes far beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description begins with 'Render animated SVG from JSON config', clearly stating the tool's core function. It distinguishes from siblings (preview, save) via workflow context, and the detailed enumeration of element types, animations, and output options reinforces the specific purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides an explicit iterative workflow ('critique, revise, render again, iterate at least 3 times'), explains when to use output options like 'svg:true', and when to preview for different widths. However, it doesn't explicitly state when not to use this tool relative to the sibling tools, though the context strongly implies it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save rendered content to disk. Format-aware: can save as text or render to raster image.
IMPORTANT: Use this only AFTER iterating on the design with render_svg's preview images. Do not save on the first render. Preview and refine your work first.
Input: pass EITHER artifact (id from render_svg, e.g. "art-1" — preferred, no SVG resend) OR content (raw string).
Format detection:
'auto' (default): infers format from file extension. .svg saves as text, .png renders to image.
'svg': saves content as a UTF-8 text file
'png': renders the content (assumed SVG) to a PNG image, then saves it
If the file already exists, a numeric counter is appended before the extension to prevent overwriting: design.svg becomes design-1.svg, then design-2.svg. The actual saved path is returned in the response.
| Name | Required | Description | Default |
|---|---|---|---|
| width | No | For raster formats (png): render width in pixels. Defaults to the source content's own declared dimensions. | |
| format | No | Output format. 'auto' infers from file extension (.svg saves as text, .png renders to image). 'svg' saves content as a UTF-8 text file. 'png' renders SVG content to a PNG image before saving. | auto |
| content | No | Raw content to save. Only needed when the content did not come from render_svg. | |
| artifact | No | Artifact id returned by render_svg (e.g. "art-1"). Preferred over content. | |
| outputPath | Yes | File path to save to. The directory must already exist. If the file already exists, a numeric counter is appended before the extension: design.svg becomes design-1.svg, then design-2.svg, and so on. The actual saved path is returned in the response. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behaviors: format detection (auto, svg, png), file overwrite prevention with numeric counter, and input options (artifact vs content). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with sections, bullet points, and bolded keywords. Every sentence earns its place—no fluff. Efficiently communicates complex behavior in a few paragraphs.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 params, no annotations, and no output schema, description covers all aspects: input selection, format handling, overwrite behavior, and return value. Complete enough for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds crucial context: width defaults to source dimensions, artifact is preferred over content, outputPath explains counter behavior, format enum values are elaborated. Adds significant value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Save rendered content to disk' and distinguishes itself from siblings (preview, render_svg) by specifying it is for final saving after iterating on design.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this only AFTER iterating on the design with render_svg's preview images' and warns 'Do not save on the first render', providing clear usage context and when-not-to-use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.3.0render_svg1 field changedInput schema / properties / output / properties / framesAdded value: +{
+ "type": "number"
+}v0.2.0preview3 fields changedInput schema / properties / artifactAdded value: +{
+ "description": "Artifact id returned by render_svg (e.g. \"art-1\"). Preferred over content.",
+ "type": "string"
+}Input schema / properties / content / descriptionPrevious value: -"SVG string to render as PNG"New value: +"SVG string to render as PNG. Only needed when no artifact id exists."Input schema / requiredRemoved value: -[
- "content"
-]render_svg6 fields changedInput schema / additionalPropertiesPrevious value: -falseNew value: +trueInput schema / properties / animations / items / additionalPropertiesPrevious value: -falseNew value: +trueInput schema / properties / animations / items / properties / keyframes / items / additionalPropertiesPrevious value: -falseNew value: +trueInput schema / properties / canvas / additionalPropertiesPrevious value: -falseNew value: +trueInput schema / properties / defs / additionalPropertiesPrevious value: -falseNew value: +trueInput schema / properties / outputAdded value: +{
+ "additionalProperties": true,
+ "properties": {
+ "minify": {
+ "type": "boolean"
+ },
+ "preview": {
+ "type": "boolean"
+ },
+ "previewWidth": {
+ "type": "number"
+ },
+ "svg": {
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+}save3 fields changedInput schema / properties / artifactAdded value: +{
+ "description": "Artifact id returned by render_svg (e.g. \"art-1\"). Preferred over content.",
+ "type": "string"
+}Input schema / properties / content / descriptionPrevious value: -"Content to save. This is typically the output of a render tool such as render_svg."New value: +"Raw content to save. Only needed when the content did not come from render_svg."Input schema / requiredPrevious value: -[
- "content",
- "outputPath"
-]New value: +[
+ "outputPath"
+]v0.1.0render_svg2 fields changedInput schema / properties / animations / items / properties / keyframes / minItemsRemoved value: -2Input schema / properties / elements / minItemsRemoved value: -1v0.1.3previewrender_svgsaveScored across 3 tools
Each tool has a clearly distinct purpose: render_svg generates SVG from config, preview renders existing or external SVG to PNG, and save persists rendered content. The overlap where render_svg includes a preview by default is explicitly handled by the preview tool's description, so no ambiguity exists.
All names use lowercase snake_case and are short, but there is a minor deviation: render_svg follows verb_noun while preview and save are bare verbs. The pattern is still predictable and readable, with only a slight structural inconsistency.
Three tools is well-scoped for a focused SVG rendering service. Each tool earns its place: render for creation, preview for inspection, save for persisting output. No unnecessary duplication or bloat.
The tool surface covers the full intended workflow: render generated content, preview it at different sizes or from external SVG, and save as text or image. There are no obvious dead ends or missing core operations for the server's stated purpose.
MCP server for Flux AI image generation
MCP server for Wan AI video generation
MCP server for Hailuo (MiniMax) AI video generation
Make animated videos by asking Claude, Cursor or any MCP client. Your AI writes it, we render it.