prompt-to-asset
Generates Android adaptive icons (including monochrome) and exports asset bundles for Android apps.
Integrates with Cloudflare Workers AI to generate assets using Flux-1-Schnell and SDXL models, with a free daily quota.
Produces Flutter launcher icons and asset bundles for Flutter projects.
Supports Google Gemini models (e.g., Nano Banana Pro) for image generation via API or Google AI Studio paste UI.
Generates iOS AppIconSet, including all required sizes and visionOS parallax icons.
Integrates with OpenAI image generation models (e.g., gpt-image-1.5) for creating assets.
Generates Progressive Web App icons (192x192, 512x512, maskable) and favicon bundles.
Generates sprite sheet atlases compatible with Unity, along with 9-slice data and border-image CSS.
30-second start
Pick one. Run it. You're done. The recommended path is first.
Runtime: Node β₯ 20.11 (24 recommended). macOS, Linux, Windows (WSL2 for --fix native deps).
π΅ AI assistant Β· recommended
Click an install button above. Then paste one of these into chat:
β’ Make a transparent logo for Forge, a dev-tools brand. Flat vector, warm orange.
β’ Make a favicon for my app, dark-mode aware.
β’ Fan this master.png out to iOS + Android + PWA.
β’ Ingest this screenshot as a mark, vectorize, export everything.Works in Cursor, Claude Code, VS Code, Windsurf, Codex, Gemini CLI. Zero terminal typing.
π’ Zero key, zero install
One curl, one npx. Offline fan-out to every platform.
curl -o logo.png \
"https://image.pollinations.ai/prompt/\
minimal+flat+vector+logo\
?model=flux&width=1024&nologo=true"
npx prompt-to-asset export logo.png \
--platforms ios,android,pwa,faviconOutputs: iOS AppIconSet, Android adaptive, PWA, favicon bundle, visionOS scaffold.
π£ CLI Β· free API keys
Best CLI experience: free tokens first, paid keys optional.
npm i -g prompt-to-asset
p2a doctor # check env
p2a doctor --fix # auto-install deps
p2a pick # interactiveStart with Cloudflare Workers AI, NVIDIA NIM, HF Inference, Stable Horde, and free trials. Paid providers remain optional fallbacks.
Free paths at a glance
You don't need a paid API key. Ranked best-first:
Route | Gets you | Signup |
| Logos, favicons, icon packs β instant | None |
Cloudflare Workers AI | Flux-1-Schnell + SDXL, 10k neurons/day | Free token + account ID |
NVIDIA NIM | Flux.1-dev, Flux.2-klein, SDXL, SANA | Free token, no card |
HF Inference | SDXL, SD3, Flux dev/schnell | Free read token |
Stable Horde | SDXL, Flux on community GPUs | Anonymous queue |
Pollinations (HTTP GET) | Last-resort raster, RGB | None |
Google AI Studio (paste-only UI) | Nano Banana / Nano Banana Pro | Google account |
Details + quotas: Free paths beyond Pollinations. Run p2a doctor or ask your assistant for asset_doctor() to see what's live right now.
Stuck? ClickInstall in Cursor or Install in VS Code above, restart the editor, and say: "make a favicon for my app, dark-mode aware."
Related MCP server: brain-mcp-icon-visual
Highlights
Free CLI-first generation β
p2a doctor,p2a pick, and the MCP tools rank free API routes before paid models, so developers can generate inside the CLI without enabling billing.Three execution modes β
inline_svg(host LLM authors SVG),external_prompt_only(paste into any web UI),api(server calls a free or paid provider). Pick what fits. All three can finish on $0.60+ models, free-first routing β Cloudflare Workers AI, NVIDIA NIM, HF, Horde, Pollinations, free trials, plus optional paid OpenAI / Ideogram / Recraft / BFL / Gemini. Each rule cites a research source.
Refuses to do the wrong thing β the
Nevercolumn. No wordmarks past 3 words through a diffusion sampler. No transparent PNG through Imagen. Nonegative_prompton Flux.Offline platform fan-out β one 1024Β² master β iOS AppIconSet, Android adaptive + monochrome, PWA 192/512/512-maskable, favicon bundle, visionOS parallax, Flutter launcher. Zero network.
Validates before shipping β tier-0 checks on every output: dims, alpha presence, checkerboard FFT, safe-zone bbox, ΞE2000 palette drift, WCAG contrast, OCR Levenshtein on wordmarks.
Sprite sheets + 9-slice β pack PNG frames into TexturePacker-compatible atlases (Phaser, PixiJS, Godot, Unity); emit 9-slice numbers + CSS
border-image+ Android.9.png.
Table of contents
Usage β what to say to your assistant
The three modes β inline_svg Β· external_prompt_only Β· api
The router β which model for which job, and what never
Models covered β 60+
MCP tools β 25 tools
Usage
You just talk to your assistant. Example from a new chat:
Make me a transparent logo for a developer-tools company called Forge. Flat vector, two-tone warm orange on neutral.
Behind the scenes:
asset_doctor()β check what modes and providers are live.asset_init_brand({ app_name: "Forge", palette: ["#EA580C", "#F5F5F4"] })if nobrand.jsonexists.asset_enhance_prompt({ brief })returns anAssetSpec: classification, rewritten prompt,modes_available[], optionalsvg_brief, optionalpaste_targets, and arouting_tracepointing at the research file that backed the decision (plusnever_modelsβ why Imagen or DALLΒ·E got rejected).Assistant offers you
inline_svg/external_prompt_only/api.If
inline_svg: it writes<svg>inline and callsasset_save_inline_svgβ writesmaster.svg,favicon.ico, apple-touch, AppIconSet, PWA bundle to disk.If
external_prompt_only: assistant shows the refined prompt and the best paste target (free first). You generate, save, then say "ingest this file" βasset_ingest_external.If
api: assistant calls the routed provider. Server mattes, vectorizes, exports, validates.Follow-up: "also fan this out for iOS and Android" β
asset_export_bundlewith the saved master.
Zero CLI typing. The CLI is still first-class for CI, shell scripts, and non-MCP environments β both surfaces hit the same core.
Why this exists
Two facts shape everything here.
Producing production-grade software assets is a routing and post-processing problem, not a prompt-engineering problem.
Imagen 3/4 and Gemini Flash Image can't produce real RGBA PNGs β their VAE is RGB-only, so asking for a transparent background renders the grey-and-white checkerboard as pixels. SDXL can't spell past ~8 characters. Only Recraft emits native SVG. Flux errors on negative_prompt. None of that is visible in the model UI. All of it silently breaks one-shot "prompt β asset" tools.
You may not have an image-model API key. The plugin works anyway.
Every one of the three modes can finish on $0.
The three modes
flowchart LR
A["one-line brief"] --> B["asset_enhance_prompt"]
B --> C{"mode"}
C -->|inline_svg| D["Host LLM emits SVG inline<br/>β asset_save_inline_svg"]
C -->|external_prompt_only| E["Paste into web UI<br/>β asset_ingest_external"]
C -->|api| F["Server calls routed provider"]
D --> G["matte Β· vectorize Β· validate"]
E --> G
F --> G
G --> H["AssetBundle<br/>ios Β· android Β· pwa Β· favicon Β· visionos Β· flutter"]Mode | Key? | What happens | Best for |
| No | Server returns an SVG-authoring brief (viewBox, palette, path budget β€ 40). Host LLM emits | Logos, favicons, icon packs, stickers, simple app-icon masters |
| No | Server returns the dialect-correct prompt plus a ranked list of paste targets, free paths first: Pollinations, HF Inference, Stable Horde, Google AI Studio, Ideogram, Recraft, Midjourney, fal.ai, BFL, ChatGPT, Firefly, Krea. Generate elsewhere, save locally, call | Anything β best for illustrations, heroes, text-heavy logos |
| Optional | Server calls the provider directly. Works zero-key via Pollinations / Horde / HF, or with paid keys. Route β generate β matte β vectorize β export β validate β content-addressed bundle. | Automation, CI, no rate-limit tolerance |
The host LLM picks the mode, or you do. The server surfaces modes_available so the assistant offers them to you. Free paths first β always.
The router
Router decisions live in data/routing-table.json. Capability matrix in data/model-registry.json. Every rule cites its research source.
Need | Primary | Fallback | Never |
Transparent PNG mark |
| Ideogram 3 Turbo ( | Imagen, Gemini Flash Image, SD 1.5 |
Logo with 1β3 word text | Ideogram 3 Turbo β | Composite SVG type over mark | Imagen, SD 1.5, |
Logo with >3 word text | Never a diffusion sampler. Mark + SVG typography composite. | β | β |
Native SVG | Recraft V4 (V3 for brand-style pipelines) |
| Everyone else |
Photoreal hero | Free CLI route first: Cloudflare / NVIDIA NIM / HF | Flux Pro / | DALLΒ·E 3, Imagen 4 for new work |
Iterate an existing mark |
| Pollinations Kontext (free) | β |
Zero-cost everything |
| Pollinations β paste-only | β |
The Never column matters. It's why prompt-to-asset refuses to render wordmarks past 3 words in any diffusion sampler, and why asking for a transparent PNG never goes to Imagen.
Free paths beyond Pollinations
Option | How | Best at | Catch |
Cloudflare Workers AI | Free API token + account ID | Flux-1-Schnell, SDXL, DreamShaper | 10k neurons/day cap (~900 Flux-Schnell or 5k SDXL-Lightning) |
NVIDIA NIM | Free API token, no card | Flux.1-dev, Flux.2-klein, SDXL, SANA | 1k requests/month; strong free CLI route |
HF Inference | Free read token | SDXL, SD3, Flux dev + schnell | Rate-limited, cold-start latency |
Stable Horde | Anonymous kudos queue | SDXL, Flux community GPUs | Minutes of queue on the free lane |
Pollinations.ai |
| Throwaway raster | Last resort: silent model swaps, downsizing, RGB only |
Google AI Studio (UI) | Free interactive web UI at aistudio.google.com | Nano Banana / Nano Banana Pro | No free API β paste-only; download PNG, call |
Local ComfyUI | Community | Full fidelity, no caps | You bring the GPU |
| Host LLM emits | Logos, favicons, simple icons | β€40 paths; simple geometry |
| Paste into any web UI | Whatever that UI gives you | Manual save, then |
Verified 2026-04-26 against public Gemini API pricing:
Imagen 4 image output is paid API. The pricing table lists Free Tier as "Not available" and prices Fast / Standard / Ultra at $0.02 / $0.04 / $0.06 per image.
Nano Banana family is paid API.
gemini-3.1-flash-image-preview(Nano Banana 2),gemini-3-pro-image-preview(Nano Banana Pro), andgemini-2.5-flash-image(original Nano Banana) list image output only in the paid tier. Billing must be enabled on the GCP project to use these via API.Free for text, multimodal understanding, and embeddings. The Gemini text-out models still have
Free of chargeinput + output on the free tier.Free interactive image generation is also via the AI Studio web UI at aistudio.google.com. Community-observed limit 500β1,000 images/day, dynamic. Use
external_prompt_only+asset_ingest_externalif you want Nano Banana quality without billing.Free image generation via the Gemini consumer app at gemini.google.com: Basic 20/day, AI Plus 50/day, AI Pro 100/day, Ultra 1,000/day.
Paid API pricing (per image, standard): Nano Banana (
gemini-2.5-flash-image) $0.039; Nano Banana 2 Flash (gemini-3.1-flash-image-preview) $0.045/0.5K, $0.067/1K, $0.101/2K, $0.151/4K; Nano Banana Pro (gemini-3-pro-image-preview) $0.134/1K-2K, $0.24/4K (+ $0.0011 per input image); Imagen 4 Fast $0.02, Standard $0.04, Ultra $0.06. Batch API is 50% off.
Run
p2a doctor(or ask your assistant forasset_doctor()) to see what's live in your environment right now.
Install
Every command works via npx β no install required.
# Zero install
npx prompt-to-asset doctor # what's live in this shell right now
npx prompt-to-asset doctor --fix # auto-install native deps (brew / cargo / scoop; never sudo)
npx prompt-to-asset pick # interactive route picker
npx prompt-to-asset init --register # scaffold brand.json + register in .cursor / .vscode / .windsurf
# Or global for daily use
npm i -g prompt-to-asset
p2a doctor
# Or per-project for CI
npm i -D prompt-to-assetRegister with your AI assistant
Claude Code
claude mcp add prompt-to-asset -- p2aSmithery (universal)
npx -y @smithery/cli install prompt-to-asset --client claudeCursor Β· VS Code Β· Windsurf Β· Codex Β· Gemini CLI
Use the install buttons at the top of this README, or see docs/install.md for the exact stanza per IDE.
Claude Desktop
Download the .mcpb bundle β double-click β restart.
Once registered, your assistant has the full 24 asset_* tool surface.
Models covered
Paid direct APIs: gpt-image-1, gpt-image-1.5, dall-e-3 (deprecated 2026-05-12), imagen-3, imagen-4, gemini-3-flash-image (Nano Banana), gemini-3-pro-image, sd-1.5, sdxl, sd3-large, playground-v3, flux-schnell, flux-dev, flux-pro, flux-2, flux-kontext-pro, ideogram-3, ideogram-3-turbo, recraft-v3, leonardo-phoenix, leonardo-diffusion-xl, fal-flux-pro, fal-flux-2, fal-sdxl.
Free-tier / zero-key: pollinations-flux, pollinations-turbo, pollinations-kontext, pollinations-sd, horde-sdxl, horde-flux, hf-sdxl, hf-sd3, hf-flux-schnell, hf-flux-dev.
Paste-only surfaces: midjourney-v6, midjourney-v7, firefly-3, krea-image-1. Calling asset_generate_* with mode: "api" against a paste-only primary soft-falls-back to the first API-reachable model in the chain and surfaces a warning. If the whole chain is paste-only, you get an ExternalPromptPlan rather than an error.
Tool | Purpose |
| Inventory of modes + providers. Buckets paid / free-tier / paste-only; surfaces zero-key routes first. Read-only. |
| Classify, route, rewrite. Returns modes + |
|
|
| Same three modes. |
|
|
| 1200Γ630 via Satori + |
|
|
| iOS |
| Marketing hero art (16:9 / 21:9 / 3:2 / 2:1). |
| Round-trip for |
| Round-trip for |
| BiRefNet / BRIA RMBG-2.0 / LayerDiffuse / difference matte / UΒ²-Net. |
|
|
| DAT2 / Real-ESRGAN / SUPIR / img2img / Lanczos; asset-type-aware. |
| Tier-0 (dims, alpha, checkerboard FFT, safe-zone bbox, ΞE2000 palette, WCAG contrast, OCR Levenshtein). Tier-2 VLM-as-judge via |
| Parse |
| Structured env inventory: native deps, free-tier routes ranked best-first, paid keys, paste-only surfaces, pipeline URLs, mode flags, "what to try next." Read-only. |
| Browse the 60+ model registry with filters: |
| Full capability dump for one model id (or aka alias). Strengths, weaknesses, paste targets, routing rules, env status. Read-only. |
| Fan a 1024Β² master PNG into iOS AppIconSet + Android adaptive + PWA maskable + visionOS parallax + Flutter launcher + favicon. Offline. |
| Pack PNG/WEBP/JPG frames into a sprite sheet + TexturePacker-compatible JSON atlas (Phaser / PixiJS / Godot / Unity). Offline. |
| Emit a 9-slice config + CSS |
| Scaffold |
| Wrap a user-owned LoRA training endpoint ( |
Tools are annotated readOnlyHint / idempotentHint so Cursor auto-approves without prompting.
Used by the LLM over Bash when MCP isn't registered yet, and by CI. Every read-only command accepts --json.
p2a # default β MCP stdio server
p2a mcp # same, explicit
p2a export <master.png> # offline platform fan-out
p2a export <master.png> --json
p2a init # interactive brand.json + IDE registration hints
p2a init --register # + auto-write .cursor/mcp.json / .vscode/mcp.json / .windsurf/mcp.json
p2a pick # interactive model picker
p2a doctor # environment inventory
p2a doctor --json # structured output
p2a doctor --data # check data/model-registry.json β data/routing-table.json consistency
p2a doctor --fix # auto-install missing native deps (brew / cargo / scoop; never sudo)
p2a models list # --free | --paid | --paste-only | --rgba | --svg
p2a models inspect <id> # full capability dump
p2a sprite-sheet <dir> # pack frames β PNG + atlas
p2a nine-slice <image> # 9-slice JSON + CSS + engine numbers + .9.png
p2a --help{
"name": "Halcyon",
"palette": ["#2563eb", "#ffffff"],
"fonts": { "display": { "family": "Inter", "weights": [700, 800] } },
"style_refs": ["https://β¦/sample1.png", "./refs/style2.png"],
"do_not": ["drop shadows", "heavy gradients"],
"lora": "halcyon-flux-v2",
"sref_code": "--sref 1234567890",
"style_id": "rc_halcyon_01"
}p2a init writes this for you, detecting the framework and suggesting an assets directory. Once present, every generator reads from it automatically.
Platform | What you get |
iOS (Xcode) |
|
Android | Adaptive foreground + background, Android 13 monochrome, all mipmap densities, optional |
PWA / web |
|
Flutter | Pre-populated |
visionOS | Three-layer parallax scaffold with a README. Layer split stays a human decision. |
Next.js / Astro / Vite / Remix / Nuxt / Expo / React Native / Electron | Framework detection via |
Games |
|
brief (text)
β asset_capabilities β modes available + free/paid/paste-only bucketing
β asset_enhance_prompt β AssetSpec {
β routing_trace: { rule_id, reason, research_sources, never_models, fallback_chain },
β modes_available,
β svg_brief?, (inline_svg)
β paste_targets?, (external_prompt_only)
β rewritten_prompt, β¦
β }
β
ββ mode: inline_svg β host LLM emits <svg>; asset_save_inline_svg writes bundle
ββ mode: external_prompt_only β user pastes into web UI; asset_ingest_external runs matte β vectorize β validate
ββ mode: api β provider(model, prompt, params) β matte β vectorize β upscale β export β validateContent-addressed storage: assets/<hash[0:2]>/<hash>/<variant>.<ext>. The MCP server is synchronous and stateless. prompt_hash and params_hash in every AssetBundle are designed to drop straight into a BullMQ / SQS / Cloudflare Queues jobId for a hosted pipeline. Reference design: docs/research/18-asset-pipeline-tools/18e-production-pipeline-architecture.md.
Design thesis
You own the API keys. The LLM owns everything else.
The only thing that happens in a terminal is installing the package and putting keys in .env. Secrets shouldn't pass through chat. Every other verb β doctor checks, model inspection, platform fan-out, brand scaffolding, sprite sheets, 9-slice configs β is an MCP tool the assistant calls when you ask in natural language.
Comparison
Tool | Prompt enhancement | Multi-model routing | Zero-key | Dev-asset bundle | Offline platform fan-out |
Promptati / PromptHero | cinematic only | β | β | β | β |
Looka / Brandmark / Designs.ai | β | β | β | partial | β |
ChatGPT / Midjourney / Ideogram (direct) | β | β | β | β | β |
appicon.co | β | β | β | partial | iOS only |
flutter_launcher_icons | β | β | β | partial | iOS + Android |
| β | β (60+ models) | β (Pollinations / HF / Horde / SVG) | β | β (iOS + Android + PWA + visionOS + favicon + Flutter) |
Security
This tool handles API keys for up to 15 providers. Non-negotiables:
Keys live in env vars only. Never written to disk, never logged, never echoed in MCP responses. Provider error bodies go through
redact()(packages/mcp-server/src/security/redact.ts) before reaching the host LLM.Path access is allow-listed.
image_path/output_dir/existing_mark_svgresolve through symlinks and reject anything escaping project cwd + configured output dir + cache dir + OS tempdir. Widen withP2A_ALLOWED_PATHS=/path1:/path2.SVG is XSS-sanitized before any write.
<script>,<foreignObject>,on*=handlers,javascript:URIs, external<image href>/<use href>, CSS@importover the network β all rejected. The check runs unconditionally; SVGO is not required.Cost guardrail. Set
P2A_MAX_SPEND_USD_PER_RUN=5.00to cap any single tool call. Pre-flight estimate refuses to call if over. Free-tier routes are always $0.Data integrity at boot.
assertDataIntegrityAtBoot()runs on start. If a routing rule points at a model id not in the registry, the server refuses to boot with a clear error. Check in CI withp2a doctor --data.No telemetry. No remote calls unless the routed provider explicitly requires one.
Full policy: SECURITY.md.
Research-backed decisions
Every routing rule, dialect switch, safe-zone size, and text ceiling that's implemented is backed by a file under docs/research/. asset_enhance_prompt returns a routing_trace.research_sources array on every call. The angle β code pointer map, plus an honest ledger of what's wired and what's deferred, lives in docs/RESEARCH_MAP.md.
Development
git clone https://github.com/MohamedAbdallah-14/prompt-to-asset.git
cd prompt-to-asset
npm install
npm run build
npm run typecheck
npm run lint
npm test # vitest watch
npm run test:run # vitest run (CI)
npm run smoke # list tools via MCP stdio + correctness assertions
npm run sync # regenerate IDE mirrors from SSOTs
npm run verify # byte-verify mirrors match SSOTsSSOTs live in skills/*/SKILL.md, rules/*.md, .claude-plugin/, and data/*.json. Don't edit .cursor/, .claude/, .windsurf/ directly β they're regenerated by scripts/sync-mirrors.sh and CI byte-verifies them.
Contribution flow: CONTRIBUTING.md
User on-ramp: GETTING_STARTED.md
Common snags: TROUBLESHOOTING.md
Release notes: CHANGELOG.md
Community
Issues + feature requests: GitHub Issues
Security disclosures: SECURITY.md
Code of Conduct: CODE_OF_CONDUCT.md
Star history:
If this repo saved you from hand-crafting another AppIconSet, a star helps it reach other developers fighting the same fight.
Read more
The thinking behind the design, in long-form:
Why I stopped picking image models and built a router instead β the case for routing across 30+ image models.
MCP server architecture: what's inside prompt-to-asset β architecture deep-dive.
Cross-posted on Medium and dev.to.
License
MIT Β© prompt-to-asset contributors.
Available Tools
24 toolsasset_brand_bundle_parseARead-onlyIdempotent
Parse a brand source (brand.json, DTCG tokens, AdCP spec, brand.md, or raw text) into the canonical BrandBundle schema.
Inputs: source (required).
asset_capabilitiesARead-onlyIdempotent
Report which of the three execution modes this server can run RIGHT NOW given the current env: inline_svg (zero key β hosting LLM authors the SVG), external_prompt_only (zero key β paste prompt into Ideogram/Nano Banana/Midjourney/Recraft/Flux UIs, then asset_ingest_external), api (requires provider key). Read-only; no network. Call before offering the user options.
Inputs: asset_type.
asset_doctorA
Structured environment inventory β MCP equivalent of p2a doctor. Returns native-dependency status (sharp, vtracer, potrace, png-to-ico, satori, resvg-js, tesseract.js, svgo), free-tier routes ranked best-first, paid-provider keys, paste-only providers, pipeline extension URLs, which modes are available right now, and a concrete 'what to try next' suggestion list. Read-only by default. Pass check_data=true to also run the model-registry/routing-table integrity check. Pass auto_fix=true to install missing native binaries (Homebrew / cargo / scoop β never sudo); pair with auto_fix_dry_run=true to preview without executing.
Inputs: check_data, auto_fix, auto_fix_dry_run.
asset_enhance_promptARead-onlyIdempotent
Classify an asset brief, route to the right model, rewrite the prompt in that model's dialect, and report which execution modes are available (inline_svg / external_prompt_only / api). Returns an AssetSpec JSON including modes_available, optional svg_brief (for inline_svg), optional paste_targets (for external_prompt_only), and β when the brief leaves a material ambiguity β a clarifying_questions[] array the host LLM should surface via AskUserQuestion (or the equivalent) BEFORE calling a generator. Each entry has {id, header, question, options[], required, why}. Read-only; idempotent; no network.
Inputs: brief (required), vector, asset_type, transparent, +3 more.
asset_export_bundleA
Fan out a 1024Β² master PNG into the full platform bundle (iOS AppIconSet, Android adaptive, PWA maskable, visionOS parallax, Flutter launcher, favicon set). MCP equivalent of p2a export master.png. No API key required; runs entirely on sharp. Use when the LLM has a master (inline_svg saved, api-mode result, or user-supplied hand-authored PNG) and needs the platform fan-out.
Inputs: master_path (required), platforms, out_dir, bg, +3 more.
asset_generate_app_iconA
Generate an app icon (iOS AppIconSet, Android adaptive, PWA maskable, visionOS 1024Β² master + placeholder parallax layers). Three modes (inline_svg / external_prompt_only / api). In non-api modes only the master mark is produced; call asset_ingest_external afterwards to run the platform fan-out. Set ios_18_appearances=true to also emit dark and tinted 1024Β² variants for iOS 18 tintable icons.
Inputs: brief (required), mode, brand_bundle, platforms, +2 more.
asset_generate_faviconA
Generate a favicon bundle (favicon-{16,32,48}.png + icon.svg + icon-dark.svg + apple-touch + PWA 192/512/512-maskable + snippet). Three modes β inline_svg is the best fit for simple glyph marks (legible at 16Γ16).
Inputs: brief (required), mode, brand_bundle, existing_mark_svg, +2 more.
asset_generate_heroA
Generate marketing-hero / landing-page banner art. Two modes (external_prompt_only / api); inline_svg is not supported. Accepts aspect_ratio (16:9 / 21:9 / 3:2 / 2:1). Injects brand bundle where supported. Returns N variants if count>1.
Inputs: brief (required), mode, brand_bundle, aspect_ratio, +2 more.
asset_generate_illustrationA
Generate one or more brand-locked illustrations. Two modes (external_prompt_only / api); inline_svg is not supported β path budget too small for a composed scene. Injects brand bundle (palette, style_refs, LoRA, style_id) where supported.
Inputs: brief (required), mode, brand_bundle, count, +2 more.
asset_generate_logoA
Generate a logo. Three modes: inline_svg (Claude emits SVG β zero key), external_prompt_only (returns prompt + paste targets β zero key), api (server runs the provider pipeline β requires key). Omit mode to auto-select. Returns an AssetBundle / InlineSvgPlan / ExternalPromptPlan discriminated by the mode field.
Inputs: brief (required), mode, brand_bundle, text_content, +2 more.
asset_generate_og_imageA
Render a 1200Γ630 OG image via Satori template (deterministic typography, no diffusion). Default mode=api renders server-side without any API key. external_prompt_only is only meaningful when with_background_image is set. inline_svg is not supported (web-font loading + precise text layout beyond LLM reach).
Inputs: title (required), mode, subtitle, template, +4 more.
asset_generate_splash_screenA
Generate a cross-platform splash-screen bundle from a brand mark. Two modes (external_prompt_only / api); inline_svg is not supported (splash screens are PNG bundles β generate a logo inline_svg first, then call this with existing_mark_svg). api mode composites the mark onto background_color and emits ios/LaunchScreen-2732.png, android/mipmap-*dpi/splash.png, android/themes-splash.xml, pwa/splash-1200.png, and a README describing how to wire each.
Inputs: brief (required), mode, brand_bundle, existing_mark_svg, +3 more.
asset_ingest_externalB
Ingest an image the user generated in an external tool (Midjourney, Nano Banana, Ideogram web, Recraft, Flux Playground, etc.) and run the matte β vectorize (where applicable) β tier-0 validation pipeline. The round-trip endpoint for external_prompt_only mode.
Inputs: image_path (required), asset_type (required), brand_bundle, expected_text, +3 more.
asset_init_brandA
Scaffold brand.json in the project root + ensure the assets dir exists. MCP equivalent of the brand.json portion of p2a init. Auto-detects the framework (Next.js, Expo, Flutter, Xcode, Astro, Vite, Remix, Nuxt, React Native, Electron, Node) and returns platform hints. Deliberately does NOT do IDE MCP registration β that's the one piece the user handles once at install time via a terminal. Call this at the start of a new project so subsequent generator calls have a brand source-of-truth and a known output dir.
Inputs: app_name (required), palette, assets_dir, display_font, +4 more.
asset_models_inspectARead-onlyIdempotent
Full capability dump for one model. MCP equivalent of p2a models inspect <id>. Accepts a model id or an aka alias. Returns the full ModelInfo record, env status, paste targets, routing rules that reference this model (as PRIMARY / fallback / NEVER), and usage notes. Read-only; no network.
Inputs: id (required).
asset_models_listARead-onlyIdempotent
List the model registry (60+ entries) with optional filters. MCP equivalent of p2a models list. Returns id, family, provider, dialect, native_rgba/svg flags, text ceiling, tier (free/paid/paste-only), key_set status. Filter flags: free, paid, paste_only, rgba, svg. Read-only; no network.
Inputs: free, paid, paste_only, rgba, +1 more.
asset_nine_sliceA
Emit a 9-slice config + CSS border-image snippet + Unity/Godot/Phaser/PixiJS-ready numbers from one image and 4 pixel offsets. Optionally also emit an Android .9.png with the 1px stretchable-region encoding. MCP equivalent of p2a nine-slice <image>.
Inputs: image (required), guides (required), out, android_9patch.
asset_remove_backgroundARead-only
Matte an image to transparent background (BiRefNet / BRIA RMBG / UΒ²-Net via remote endpoint; local white-chroma fallback). Returns RGBA PNG path.
Inputs: image (required), mode, output_dir.
asset_save_inline_svgA
Round-trip endpoint for inline_svg mode. After you (the LLM) emit the β¦ in chat, immediately call this tool with that SVG text so the server writes a complete asset bundle to disk: master.svg + (for favicon) icon.svg + icon-dark.svg + favicon-{16,32,48}.png + favicon.ico + apple-touch-icon.png (opaque) + pwa-192.png + pwa-512.png + pwa-512-maskable.png + manifest.webmanifest + head-snippet.html + (for app_icon) the full iOS AppIconSet + Android adaptive (foreground+background+monochrome) + PWA maskable + visionOS. Returns an AssetBundle with file paths the user can open. Validates the SVG against the original svg_brief (viewBox, path count, palette, forbidden elements).
Inputs: svg (required), asset_type (required), brand_bundle, expected_text, +6 more.
asset_sprite_sheetA
Pack a directory of PNG/WEBP/JPG frames into one sprite sheet + TexturePacker-compatible JSON atlas (works in Phaser, PixiJS, Three.js, Godot, Unity via a light importer). MCP equivalent of p2a sprite-sheet <dir>. Offline, no API key.
Inputs: dir (required), layout, columns, padding, +2 more.
asset_train_brand_loraA
Train a brand-consistent LoRA from 20-50 sample images, returning a lora_id the comfyui-* and SDXL-family providers can reference. Requires a user-owned training endpoint (Modal / Runpod / self-host) at PROMPT_TO_BUNDLE_MODAL_LORA_TRAIN_URL. Phase-4 scaffold: the MCP tool does the packaging, validation, and HTTP; the user owns the deployment and pricing. See docs/research/06-stable-diffusion-flux/6d-lora-training-for-brand-style.md.
Inputs: name (required), training_images (required), base_model, captions, +2 more.
asset_upscale_refineBRead-only
Upscale / refine an image, asset-type-aware. DAT2 for flat logos/icons, Real-ESRGAN/SUPIR for photoreal, img2img for diffusion polish. Lanczos fallback.
Inputs: image (required), asset_type, target_size, mode, +1 more.
asset_validateBRead-onlyIdempotent
Run tier-0 deterministic validators on an asset (dimensions, alpha presence, checkerboard-pattern heuristic on tile-luma alternation, safe-zone bbox, palette ΞE2000 against brand, WCAG contrast of brand primary vs light and dark tabs, OCR Levenshtein against intended_text). Optional tier-2 VLM-as-judge via PROMPT_TO_BUNDLE_VLM_URL.
Inputs: image (required), asset_type (required), brand_bundle, intended_text, +1 more.
asset_vectorizeBRead-only
Convert a raster image to SVG. Tries in order: Recraft /vectorize (if PROMPT_TO_BUNDLE_RECRAFT_VECTORIZE_URL is set), vtracer on PATH, potrace on PATH, then a built-in posterize run-length fallback. Passes all output through SVGO when installed.
Inputs: image (required), mode, palette_size, max_paths, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 24 tools
The asset_generate_* family is clearly separated by output artifact, and the processing, ingestion, validation, and export tools have mostly distinct jobs. The main ambiguity is between asset_doctor and asset_capabilities, which both report currently available execution modes, and asset_export_bundle vs asset_save_inline_svg both create platform bundles from different input types.
All tools share the asset_ prefix and snake_case, so the surface is readable, but the internal convention is inconsistent: verb-first names like asset_generate_logo and asset_init_brand coexist with object-first names like asset_models_list, asset_models_inspect, and asset_brand_bundle_parse, plus noun-only names like asset_sprite_sheet and asset_capabilities. The asset_generate_* subfamily is consistent, but the rest does not follow one clearly predictable pattern.
At 24 tools, the set is at the heavy/borderline end for an MCP server: each tool has a real purpose, but several generate_* variants and model/doctor helpers could be consolidated or parameterized to make the surface easier for an agent to discover. The count is not egregious, but it is above the ideal compact size.
The tool surface covers the full lifecycle from brand ingestion and prompt enhancement through generation, saving/ingestion, validation, vectorization, upscaling, background removal, platform export, sprite sheets, 9-slice config, model inspection, and environment diagnosis. Every execution mode has a clear follow-up path, so the workflow does not end in a dead end.
Maintenance
Related MCP Connectors
Generate PWA icon sets and iOS splash screens from a text prompt or an existing image.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models and 10 tools: up to 4 images per call, SVG vectorization, editing and more. Remote MCP with OAuth, no API keys. Pay per image, no subscription.
Check, generate, and troubleshoot complete favicon, Apple touch icon, PWA, and web app icon sets.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceGenerates all required web app icons and manifest files from a single source image with framework auto-detection. Supports Next.js App Router, traditional web apps, and PWA standards with zero configuration.15 npmMIT
- FlicenseNot gradedqualityDmaintenanceVisual icon search, retrieval, and comparison for AI agents. Search 200k+ icons semantically, render side-by-side comparison grids, and retrieve raw SVG markup β all tools return images so vision-capable LLMs can see the icons.1-
- AlicenseCqualityCmaintenanceGenerate deployment-ready PWA, iOS, and Android app icon sets from a text description. Produces all 27 required sizes, maskable icons, Xcode-ready iOS icons, Android mipmap folders, splash screens, and manifest.json packaged as a ZIP. Powered by Google Imagen 4.62MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search 2000+ bundled Lucide icons by keyword and generate one or many styled SVGs with consistent stroke width, color, and size, entirely offline without API keys.MIT