Prompt To Asset

What MohamedAbdallah-14/prompt-to-asset MCP server does

MohamedAbdallah-14/prompt-to-asset MCP server turns an asset brief or existing image into outputs used by web and application projects. Generation tools cover logos, app icons, favicons, Open Graph images, illustrations, splash screens, and marketing heroes. It can also process supplied assets by removing backgrounds, vectorizing raster images, upscaling or refining them, and running validation checks.

The project is designed around three execution paths. inline_svg lets the host language model author an SVG without credentials. external_prompt_only produces a model-specific prompt and paste destinations for services such as Ideogram, Nano Banana, Midjourney, Recraft, or Flux interfaces. api lets the server call configured image providers. The available paths depend on the current environment and the asset type.

How it works

A typical workflow starts with asset_capabilities or asset_doctor, which reports the modes and provider routes currently available. asset_enhance_prompt classifies a brief, selects a suitable model, adapts the wording to that model, and returns an AssetSpec. If important details are unclear, it provides questions for the host assistant to ask before generation.

Generated or supplied masters can be passed to asset_export_bundle for platform-specific outputs. For inline SVG, the assistant should send the completed markup to asset_save_inline_svg, which writes the SVG and related files to disk. Images made in an external UI can return through asset_ingest_external, which applies the available matte, vectorization, and tier-0 validation steps.

Brand consistency is handled through asset_brand_bundle_parse, which accepts sources such as brand.json, DTCG tokens, AdCP specifications, brand markdown, or raw text. A brand bundle can provide palette, style, and related model settings where supported. asset_train_brand_lora packages and submits training data to a user-owned training endpoint; it does not provide that deployment itself.

Setup and configuration

The package requires Node.js 20.11 or newer. The MCP server can be launched with npx -y prompt-to-asset. The README also documents npm installation and client-specific installation links for Cursor, VS Code, and Claude Desktop; Windsurf is listed as a supported assistant environment.

No credential is needed for inline SVG, external prompt handoff, offline bundle export, sprite sheets, 9-slice generation, or other local operations. API-backed routes may use Cloudflare Workers AI, NVIDIA NIM, Hugging Face Inference, Stable Horde, Pollinations, free trials, or optional paid providers. Provider availability and credentials can be inspected with asset_doctor or asset_models_list.

Tools and capabilities

• Generate logos, icons, favicons, OG images, illustrations, splash screens, and hero artwork.
• Export a 1024² master into iOS, Android, PWA, favicon, visionOS, and Flutter outputs.
• Build TexturePacker-compatible sprite atlases and 9-slice configuration files.
• Parse brand sources and apply palette, style, and text-related constraints.
• Validate dimensions, transparency, safe zones, palette drift, WCAG contrast, and OCR similarity.
• Inspect a registry of more than 60 models, including routing rules and credential status.

Limitations and notes

Not every asset type supports every execution mode. OG images use a deterministic Satori template and do not support inline SVG; external prompting is relevant only when a background image is requested. Illustrations, splash screens, and hero art support external prompting and API execution but not inline SVG. App icons generated through non-API modes produce the master mark first, after which platform fan-out requires another tool call.

API-backed generation depends on provider configuration, quotas, endpoint availability, and model capabilities. Background removal can use remote endpoints or a local white-chroma fallback, while vectorization falls back through local tools and a built-in posterization method. LoRA training requires a user-owned Modal, RunPod, or self-hosted endpoint. Native dependencies such as sharp, vtracer, potrace, satori, resvg-js, tesseract.js, and svgo are optional capabilities that can affect results.