@agentutility/mcp-synthforge 0.1.8 → 0.7.0

package/README.md

@@ -2,7 +2,7 @@
 
 > Generative media for agents that ship products.
 
-Image, video, music, voice generation across three price tiers. One API surface, USDC-settled, no SaaS account.
+Image, video, music, and voice generation with fast Venice models, pro creative models, and flagship Google/OpenAI image tiers. One API surface, USDC-settled, no SaaS account.
 
 **Pricing:** pay-per-call in USDC on Base. No subscriptions, no API keys. See per-tool prices below.
 
@@ -22,7 +22,7 @@ Edit `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) o
 }
 ```
 
-Restart Claude Desktop. 14 tools appear in the tool palette.
+Restart Claude Desktop. 52 tools appear in the tool palette.
 
 ## Install — Cursor
 
@@ -46,10 +46,29 @@ Send any amount of **USDC on Base mainnet** to the address derived from your `X4
 
 USDC on Base contract: `0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`
 
-## Tools (14)
+## Tools (52)
 
 | Tool | Description |
 |---|---|
+| `ad-banner-image-expand` | (0.15 USDC/call) Ad banner image expand API / paid social canvas outpaint / campaign creative extender. Same Bria Expand backend as image-expand, tuned for agents adapting existing images into wide, square, or portrait ad placements. |
+| `ad-creative-image-generate` | (0.01 USDC/call) Ad creative image generator API / campaign visual generator / paid social creative. Same backend as image-generate, listed for agents producing SFW marketing visuals, concept images, and campaign thumbnails from prompts. |
+| `app-icon-image-generate` | (0.01 USDC/call) App icon generator API / mobile icon concept / SaaS icon image generation. Same image-generate backend, listed for agents making SFW square icon concepts, product marks, and launch visuals. |
+| `app-store-screenshot-expand` | (0.15 USDC/call) App store screenshot expand API / mobile screenshot backdrop extender / launch asset outpaint. Same Bria Expand backend as image-expand, listed for agents adapting screenshots into store, ad, and product-page layouts. |
+| `background-remove` | (0.08 USDC/call) Background remove API / image background remover / transparent PNG foreground cutout. Removes the background from a public image URL and returns the subject with alpha transparency. Optional crop_to_bbox. fal.ai imageutils/rembg. |
+| `background-remover` | (0.08 USDC/call) Background remover API / remove image background / transparent PNG cutout. Same remove-bg backend, listed for agents turning product, portrait, and object images into alpha PNG foreground cutouts with optional crop-to-bounding-box behavior. |
+| `banner-image-expand` | (0.15 USDC/call) Banner image expand API / hero image outpainting / website header extender. Same backend as image-expand, exposed for agents turning existing photos into wide website, ad, and email-header canvases. |
+| `blog-header-image-generate` | (0.01 USDC/call) Blog header image generator API / article hero image / editorial illustration generator. Same backend as image-generate, discoverable for agents creating SFW header images, newsletter visuals, and documentation illustrations. |
+| `book-cover-image-generate` | (0.01 USDC/call) Book cover image generator API / ebook cover concept / publishing creative. Same image-generate backend, listed for agents creating SFW cover art concepts, genre mood boards, and launch visuals from a prompt. |
+| `brand-logo-concept-image` | (0.01 USDC/call) Brand logo concept image API / startup logo visual ideation / mark concept generator. Same fast Venice-backed backend as image-generate, exposed for agents creating SFW logo concept boards, abstract marks, and brand direction visuals from prompts. |
+| `course-thumbnail-expand` | (0.15 USDC/call) Course thumbnail expand API / tutorial cover outpaint / education hero image extender. Same image-expand backend, surfaced for agents adapting existing screenshots, instructor photos, or diagrams into 16:9 course thumbnails. |
+| `course-thumbnail-image-generate` | (0.01 USDC/call) Course thumbnail image generator API / education cover art / tutorial hero image. Same fast image-generate backend, discoverable for agents creating SFW course thumbnails, lesson covers, learning-path artwork, and academy launch visuals without text rendering. |
+| `ecommerce-lifestyle-image-generate` | (0.01 USDC/call) Ecommerce lifestyle image generator API / product lifestyle creative / marketplace campaign image. Same image-generate backend, listed for agents creating SFW lifestyle scenes and ad visuals around product prompts. |
+| `email-header-image-expand` | (0.15 USDC/call) Email header image expand API / newsletter banner outpaint / lifecycle email creative extender. Same image-expand backend, exposed for agents adapting existing product, event, or editorial images into wide email-header canvases. |
+| `event-poster-image-generate` | (0.01 USDC/call) Event poster image generator API / conference visual / meetup campaign image. Same fast image-generate backend, exposed for agents producing SFW event artwork, launch posters, and campaign backgrounds without relying on stock art. |
+| `fashion-lookbook-image-generate` | (0.01 USDC/call) Fashion lookbook image generator API / apparel campaign visual / style mood board. Same image-generate backend, listed for agents producing SFW clothing concepts, seasonal lookbook scenes, and ecommerce fashion creative from prompts. |
+| `game-asset-concept-image` | (0.01 USDC/call) Game asset concept image API / character prop environment concept generator. Same image-generate backend, exposed for agents drafting SFW game art concepts, item thumbnails, environment mood boards, and prototype visual assets. |
+| `healthcare-campaign-image-generate` | (0.01 USDC/call) Healthcare campaign image generator API / clinic marketing visual / wellness program creative. Same image-generate backend, discoverable for agents creating SFW healthcare, wellness, clinic, and patient-education campaign visuals without medical claims. |
+| `image-describe-api` | (0.02 USDC/call) Image describe API / image captioning / alt text generator. Same image-description backend, exposed for agents producing captions, accessibility alt text, short descriptions, and visual summaries from public image URLs. |
 | `image-edit` | (0.02 USDC/call) Image edit / instruction-based image edit / text-driven photo edit / nano-banana image editor / GPT-image-2 edit. Mask-free instruction-driven image editing — describe the change in text and the model applies it to the whole image. Default model: nano-banana-pro. Returns a permanent fal-hosted PNG URL. |
 | `image-expand` | (0.15 USDC/call) AI image outpainting / image expansion. Bria Expand model. Generates realistic content beyond original borders. Set canvas size + original placement. Commercial-license model. |
 | `image-generate` | (0.01 USDC/call) Image generate (fast/cheap) / text-to-image / AI art. SFW, sub-5s turnaround. Four tiers backed by curated $0.01 Venice models: 'fast' (z-image-turbo, default), 'creative' (chroma), 'anime' (wai-Illustrious), 'sd35' (venice-sd35). For top-tier quality use image-generate-pro ($0.10, Flux 2 Pro / Recraft / Seedream / Qwen Image 2 Pro) or image-generate-ultra ($0.30, Google nano-banana-pro / OpenAI gpt-image-2). Returns a permanent fal-hosted PNG URL. |
@@ -57,18 +76,37 @@ USDC on Base contract: `0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`
 | `image-generate-ultra` | (0.30 USDC/call) Image generate (ultra) / flagship text-to-image / Google nano-banana-pro (Gemini Image 3) / OpenAI gpt-image-2 / Recraft V4 Pro / xAI Grok SOTA. Top proprietary models for the highest quality output. Tiers: 'nano-banana' (nano-banana-pro, default — Google Gemini Image 3), 'nano-banana-2' (cheaper Google variant), 'gpt' (gpt-image-2 — OpenAI flagship), 'gpt-1-5' (gpt-image-1-5), 'recraft-pro' (recraft-v4-pro), 'grok-sota' (grok-imagine-image-quality). Output is capped to 1024x1024 to keep wholesale within retail; for higher resolution, chain image-upscale. Returns a permanent fal-hosted PNG URL. |
 | `image-inpaint` | (0.02 USDC/call) Image inpainting / mask-based image edit / fill in masked region / object replacement / face swap (mask-driven) / generative fill. Replaces the masked region of an image with content matching a text prompt. White pixels in the mask = region to inpaint. Default model: gpt-image-2. Returns a permanent fal-hosted PNG URL. |
 | `image-to-video` | (0.20 USDC/call) Image-to-video / animate still image / Seedance image-to-video / motion-from-photo / camera-movement on photo. Animates a still image into video via Venice's seedance-2-0-fast-image-to-video. Optional prompt steers the motion (camera moves, subject motion). Same async-vs-sync handling as text-to-video. |
+| `linkedin-banner-expand` | (0.15 USDC/call) LinkedIn banner expand API / profile header outpainting / brand banner image extender. Same Bria Expand backend as image-expand, discoverable for agents turning existing photos into wide social-profile headers. |
+| `marketplace-product-expand` | (0.15 USDC/call) Marketplace product image expand API / ecommerce photo canvas extender / product listing outpaint. Same Bria Expand backend as image-expand, tuned for agents adapting product shots to marketplace, catalog, and ad aspect ratios. |
+| `mobile-story-image-expand` | (0.15 USDC/call) Mobile story image expand API / vertical social outpaint / Instagram TikTok story extender. Same image-expand backend, discoverable for agents converting existing images into tall story, reel-cover, and short-form promotional canvases. |
 | `music-generate` | (0.05 USDC/call) Music generation / text-to-music / AI music / generative song / instrumental and vocal music. Text-to-music via Venice with the minimax-music-v26 model. Optional lyrics input. Duration 5-120 seconds. Returns a permanent fal-hosted audio URL (or a Venice-hosted URL when Venice already provides one). |
-| `remove-bg` | (0.08 USDC/call) AI background remover / background eraser / cutout tool. Returns transparent PNG. Optional crop_to_bbox. fal.ai imageutils/rembg. |
+| `newsletter-image-generate` | (0.01 USDC/call) Newsletter image generator API / email header illustration / editorial campaign visual. Same image-generate backend, listed for agents creating SFW newsletter artwork, digest headers, and publication graphics. |
+| `podcast-cover-expand` | (0.15 USDC/call) Podcast cover expand API / episode art outpaint / square artwork canvas extender. Same image-expand backend, surfaced for agents adapting guest photos, product images, or show art into podcast-cover dimensions. |
+| `podcast-cover-image-generate` | (0.01 USDC/call) Podcast cover image generator API / episode art / show artwork concept. Same Venice-backed image-generate backend, discoverable for agents creating SFW square cover concepts, guest episode art, channel thumbnails, and audio-show campaign visuals. |
+| `presentation-hero-image-generate` | (0.01 USDC/call) Presentation hero image generator API / pitch deck visual / slide cover image. Same image-generate backend, discoverable for agents creating SFW deck openers, product narrative visuals, and board-slide hero images. |
+| `product-image-generate` | (0.01 USDC/call) Product image generator API / ecommerce product creative / marketplace listing image generation. Same fast Venice-backed backend as image-generate, exposed for agents creating SFW product concepts, studio-style mockups, and catalog creative from prompts. |
+| `product-photo-background-expand` | (0.15 USDC/call) Product photo background expand API / ecommerce product outpaint / studio backdrop extender. Same image-expand backend, listed for agents converting tight product crops into marketplace, catalog, and lifestyle ad canvases. |
+| `product-photo-expand` | (0.15 USDC/call) Product photo outpainting API / ecommerce image expand / product hero image extender. Same Bria Expand backend as image-expand, listed for product-detail pages, marketplaces, and catalog creative that need a larger canvas around an existing product shot. |
+| `real-estate-ad-image-generate` | (0.01 USDC/call) Real estate ad image generator API / property campaign visual / listing promotion creative. Same image-generate backend, listed for agents producing SFW property marketing visuals, neighborhood concept art, open-house ads, and listing campaign backgrounds. |
+| `real-estate-hero-expand` | (0.15 USDC/call) Real estate hero image expand API / listing banner outpaint / property website image extender. Same image-expand backend, listed for agents turning room, exterior, and neighborhood photos into wide property-page and ad hero canvases. |
+| `real-estate-photo-expand` | (0.15 USDC/call) Real estate photo outpainting API / property listing image expand / room photo canvas extender. Same backend as image-expand, listed for listing creatives that need a wider hero crop or vertical social version from an existing room or exterior image. |
+| `real-estate-render-generate` | (0.01 USDC/call) Real estate render generator API / property marketing image / interior concept visual. Same image-generate backend, discoverable for agents producing SFW listing concepts, room mood boards, exterior concepts, and property campaign visuals. |
+| `remove-background` | (0.08 USDC/call) Remove background from image / background remove API / transparent PNG cutout. Takes an image URL and returns the subject as a PNG with alpha channel. Optional crop_to_bbox. fal.ai imageutils/rembg. |
+| `remove-bg` | (0.08 USDC/call) Remove background from image / AI background remover / background eraser / transparent PNG cutout tool. Returns a foreground cutout with alpha channel. Optional crop_to_bbox. fal.ai imageutils/rembg. |
+| `restaurant-menu-image-generate` | (0.01 USDC/call) Restaurant menu image generator API / food concept visual / hospitality creative. Same image-generate backend, surfaced for agents creating SFW dish concepts, menu hero visuals, and local restaurant ad creative. |
 | `seedance-video` | (0.20 USDC/call) Seedance 2.0 / Seedance 2.0 video generation / Seedance video AI / generative AI video / text-to-video AI / cinematic AI clips on AI Gateway. Powered by Venice's seedance-2-0-fast-text-to-video model. Duration / aspect-ratio / resolution configurable. Same backend as text-to-video under a model-named slug for direct discovery by agents searching for 'Seedance'. |
+| `social-crop-expand` | (0.15 USDC/call) Social crop expand API / Instagram TikTok LinkedIn crop extender / image aspect-ratio outpainting. Same backend as image-expand, discoverable for agents adapting one image into square, portrait, landscape, and banner canvases. |
+| `social-image-generate` | (0.01 USDC/call) Social image generator API / post visual generator / LinkedIn X Instagram creative. Same backend as image-generate, exposed for agents generating SFW social images in square, portrait, and landscape sizes. |
 | `sound-effect-generate` | (0.01 USDC/call) Sound effect generation / text-to-SFX / Foley generator / ElevenLabs sound effects / ambient audio synth. Text-to-SFX via Venice with elevenlabs-sound-effects-v2. Duration 0.5-22 seconds. Returns a permanent fal-hosted audio URL (or Venice-hosted when applicable). |
-| `text-to-speech` | (0.05 USDC/call) Text to speech / TTS / voice generator. Venice TTS (Kokoro / xAI / ElevenLabs / Orpheus / MiniMax / Gemini). 30+ voices, 6 audio formats. Returns hosted MP3 URL. |
+| `text-to-speech` | (0.05 USDC/call) Text to speech / TTS / voice generator. Morpheus primary for Kokoro, Venice fallback and alternate TTS models (xAI / ElevenLabs / Orpheus / MiniMax / Gemini), with fal.ai storage for hosted audio URLs. 30+ voices, 5 audio formats. |
 | `text-to-video` | (0.20 USDC/call) Text-to-video / AI video / Seedance / generative video / cinematic clip from prompt. Text-to-video via Venice's seedance-2-0-fast-text-to-video. Duration / aspect-ratio / resolution configurable. The synchronous path has a 22s budget; if Venice can't return inline within that window, the response surfaces a job_id + poll_url for the caller to resolve later. |
 | `voice` | (0.05 USDC/call) Text-to-speech / TTS / voice synthesis. Venice TTS (Kokoro/xAI/ElevenLabs/Orpheus/MiniMax). 30+ voices, MP3/WAV/OPUS/AAC/FLAC. |
+| `youtube-thumbnail-expand` | (0.15 USDC/call) YouTube thumbnail expand API / video thumbnail outpaint / 16:9 image extender. Same Bria Expand backend as image-expand, exposed for agents adapting source images into thumbnail and video-cover canvases. |
 
 ## How it works
 
-1. Agent calls a tool (e.g. `image-edit`).
-2. MCP server POSTs to `https://x402.agentutility.ai/image-edit`.
+1. Agent calls a tool (e.g. `ad-banner-image-expand`).
+2. MCP server POSTs to `https://x402.agentutility.ai/ad-banner-image-expand`.
 3. The endpoint responds **HTTP 402** with payment instructions.
 4. The MCP server signs an EIP-3009 USDC transfer authorization with `X402_PRIVATE_KEY` and retries.
 5. CDP facilitator settles on Base.
@@ -84,4 +122,4 @@ The agent never sees the payment flow — it just gets the result.
 
 ---
 
-**Version:** 0.1.8 · **License:** MIT
+**Version:** 0.7.0 · **License:** MIT