MCP tool reference · #84 of 563 by publishers
generate_image
Exposed by 23 servers from 22 publishers, read from the live servers by the Serverdex check; most of them sit in Media & Creative; 95.7% of them take a prompt parameter; the most-starred is Magic Hour (10 stars).
generate_image(prompt: string, model?: string, aspect_ratio?: string, idempotency_key?: string, …)Parameters
share = % of the 23 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| prompt | string | 95.7% | 86.4% | Description of the image to generate. |
| model | string | 60.9% | 28.6% | image model id from hermoso_capabilities. A model whose `refs.mode` is "edit" there (gpt-image-2.6, gpt-image-2.5) takes your refImages on ITS OWN editor, up to |
| aspect_ratio | string | 30.4% | 0% | Aspect ratio of the generated image. Omit for the default: 1:1 — except an edit with flux-3-image, flux-3-image-klein, nano-banana-2.1 or mai-image-2.7, which k |
| idempotency_key | string | 26.1% | 0% | chosen once, resent unchanged on retries: the same key never buys twice |
| aspectRatio | string | 21.7% | 0% | e.g. '1:1', '9:16', '16:9', '4:5'. Each model draws its own list (hermoso_capabilities prints it per model, e.g. Nano Banana 2 goes to 1:8 and 8:1); a ratio the |
| background | string | 21.7% | 0% | transparent = a PNG with NO background (alpha channel): a cut-out product, icon, sticker or logo to place on anything. Runs on gpt-image-2.6 (default) or gpt-im |
| quality | string | 21.7% | 0% | Optional output quality. |
| resolution | string | 21.7% | 0% | For models that support it: "1K" or "2K". |
| size | string | 17.4% | 0% | Image size as width x height, e.g. 1024x1024 (square), 1792x1024 (wide), 1024x1792 (tall), 1024x768 (4:3). Made in the closest shape the model renders. |
| style | string | 17.4% | 25% | Optional style direction (e.g. 'flat vector, neon palette'). Merged into the generation prompt by Frenchie. |
| format | string | 13% | 0% | the file to make (default png). gif = an ANIMATED GIF, a short loop with no sound (describe the subject, the motion and the loop); svg = an editable VECTOR (log |
| seed | integer | 13% | 0% | Random seed for reproducible output |
Source: the input schema each server returns for generate_image, aggregated over the 23 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with generate_image
23 of 23 · 22 publishers · 23 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes generate_image |
|---|---|---|---|---|---|---|
| 1 | Magic Hourmagichourhq · Media & Creative | magichourhq | Media & Creative | 10 | yes | Generates one or more images from a text prompt, with model, output size and image count options. Costs credits; returns a project id for wait_for_image_project. Before choosing settings, read get_account_info and the current parameter constraints. A listed model, resolution, duration or count is not necessarily available together or on this account. Preserve explicit requirements and all supplied |
| 2 | openFlowmolkex · Media & Creative | molkex | Media & Creative | 10 | yes | Generate an image from a text prompt via Google Flow. model — pass ONE of these exact ids (from GET v1/flow/models, verified 2026-07-25): BELUGA = "Nano Banana 2" — the DEFAULT, ~30s (legacy id NARWHAL is accepted as an alias) GEM_PIX_2 = "Nano Banana Pro" — highest quality, ~40s, has a separate DAILY per-account quota ( |
| 3 | Hermoso: AI Ad Generatorhermoso-ai · Developer Tools | hermoso-ai | Developer Tools | 9 | yes | Use this when the user asks for an image ad, ad creative, product photo or social post graphic for their business or product, or an ANIMATED GIF (format gif) or SVG file (format svg). It renders a finished image on a real image model, on their saved brand (product photos, logo), and returns a URL ready to post. For a video, use render_ad. The saved brand’s product photo is used automatically (see |
| 4 | Hermosohermoso-ai · Other | hermoso-ai | Other | 8 | yes | Use this when the user asks for an image ad, ad creative, product photo or social post graphic for their business or product, or an ANIMATED GIF (format gif) or SVG file (format svg). It renders a finished image on a real image model, on their saved brand (product photos, logo), and returns a URL ready to post. For a video, use render_ad. The saved brand’s product photo is used automatically (see |
| 5 | com.budgetpixel MCPbudgetpixel-ai · Media & Creative | budgetpixel-ai | Media & Creative | 3 | yes | Use this to create or edit an AI image. Text-to-image from a prompt, OR image-to-image / editing / multi-reference by passing input_images (URLs, data URIs, or base64) — e.g. edit or restyle an image the user just generated by passing its URL. Input support is per-model: some take 1 image, some several, some none (check each model's max_input_images via list_models). Submits an async job and retur |
| 6 | Sats4AI - Bitcoin-Powered AI Toolscnghockey · Communication | cnghockey | Communication | 2 | yes | Generate an image from a text prompt. Returns JSON with image URL. Models: Grok Imagine 2 (fast creative generation, 100 sats), Seedream 5 Pro (most permissive content policy, 150 sats at 1K / 300 at 2K), GPT Image 2.6 (ranked #1 on the Artificial Analysis text-to-image leaderboard as of November 2026 at its maximum quality setting; this API uses the automatic setting; 1200 sats, default). Support |
| 7 | Kleapkleaphq · Search & Web | kleaphq | Search & Web | 1 | yes | Put a REAL photo or illustration on the site by describing it — no image bytes to send. Give a vivid `prompt` and a `public/` `path` (e.g. public/hero.jpg); Kleap generates it with Cloudflare FLUX.2 and stores it as a proper binary asset, exactly like write_files with encoding:"base64" but with NO base64 to transmit (a real image's base64 is too big for a model to emit reliably — this is the ONLY |
| 8 | AIPayGendamien829 · Search & Web | damien829 | Search & Web | — | yes | Create an original image from a text prompt with FLUX.1 [schnell]: illustrations, product shots, logos, thumbnails, concept art. Returns a 1024x1024 JPEG as a base64 data URL ready to save or display. Costs $0.01 per call. |
| 9 | KeelRouterkeelrouter · Media & Creative | keelrouter | Media & Creative | — | yes | Generate an image with a KeelRouter model. Spends real USD from the account balance at the price in list_models (from under $0.01 per image; higher resolutions cost more); failed calls are not charged. Waits up to 50 seconds; if not done, returns task_id for get_result. Result links are valid for a limited time. |
| 10 | Cormak.appecabpro-sudo · Security & Identity | ecabpro-sudo | Security & Identity | — | yes | Create and save a Photo Studio image for two shared Cormak credits. The owner must approve the exact request in Cormak. Requires Cormak OAuth. |
| 11 | com.pixfaro MCPdariaworks · Media & Creative | dariaworks | Media & Creative | — | yes | Generate an image from a text prompt. Returns a hosted URL plus cost and balance. Slow models (mode "async" in list_models) return a j_… job id instead — poll it with check_job. |
| 12 | aicutaicut-pro · Media & Creative | aicut-pro | Media & Creative | — | yes | Generates an AI image on the signed-in aicut account and puts the aicut card in front of the user. It waits for the image server-side for as long as one request safely can (about 24 seconds), so it usually returns the finished image with its `url` directly. WHEN: the user asks for an image. Call `list_models` first if you have not this session (an unpublished combination is rejected). `get_recipe` |
| 13 | ViewMax MCPbytevirts · Media & Creative | bytevirts | Media & Creative | — | yes | Create an image generation task (text-to-image, or image-to-image when image_urls are provided). Pro/Ultra flagship models (GPT Image 2, GPT Image 2.5, Nano Banana 2, Grok Imagine) and Ultra ViewMax C1 cost 0 credits within the shared daily fair-use pool; otherwise this consumes credits. Call wait_for_task with the task_id for the result URLs. |
| 14 | UberLLMpsa-team-source · Media & Creative | psa-team-source | Media & Creative | — | yes | Make pictures from a prompt. Spends from your balance; the answer carries the links and what it cost (usage.cost_usd). |
| 15 | Easy-Peasy.AIeasy-peasy-ai · Media & Creative | easy-peasy-ai | Media & Creative | — | yes | Generate or edit an image with Easy-Peasy.AI. Synchronous — returns image URL(s) when generation finishes (can take up to a few minutes). Uses image credits and requires a paid plan for API access. To edit existing images, pass their URLs in source_images; model then picks the edit model. display_media shows the returned image IDs in an embedded gallery. |
| 16 | MisarPost MCP Servermisar-ai · Productivity | misar-ai | Productivity | — | yes | Generate an image for a post from a text prompt, sized for the platform (16:9 for X, LinkedIn and YouTube, square for Instagram and Threads, 9:16 for TikTok), and store it in the user's media. Returns its URL to attach to a post. Uses one AI image action from the plan's quota. Nothing is posted. |
| 17 | AI Content Dropaicontentdrop · Media & Creative | aicontentdrop | Media & Creative | — | yes | Make an AI image: a product still, a thumbnail, a poster, concept art, or a reference frame to animate later. Requires a quote_id from estimate_credit_cost so the price is agreed first; then returns a job id to poll with get_generation (kind "image"). Credits are charged only when the image succeeds. SIGN-IN REQUIRED: connect this server with OAuth (the host prompts for it), or add an API key head |
| 18 | GenMagicyumaheymans · Media & Creative | yumaheymans | Media & Creative | — | yes | Generate an image from a text description with GenMagic. Pass 'image' (an https or data URL) to transform THAT image instead of generating from scratch (image-to-image), and type "logo" to make a brand mark. Returns the image inline plus a hosted URL. On-brand automatically when the account has brand personalization on. |
| 19 | Store APIkirials86-eng · AI & Agents | kirials86-eng | AI & Agents | — | yes | Generate an image from a text prompt and return a link to it. — Сгенерировать изображение по описанию, возвращает ссылку. |
| 20 | SocialHivejalal1985khan · Marketing & SEO | jalal1985khan | Marketing & SEO | — | yes | Generate an image into the media library and return its asset id (attach with create_post.mediaIds). quality 'free' uses the free provider; 'hq' costs credits. |
| 21 | Chip MCPzapret-digital · Communication | zapret-digital | Communication | — | yes | Сгенерировать картинку 1024×1024. ПЛАТНО: списывает с баланса пользователя ~9 кредитов — зови по его запросу, не «на пробу». С project_id PNG ляжет в файлы проекта, без него — временная ссылка, скачай сразу. |
| 22 | FavCRMfavcrm · Business & CRM | favcrm | Business & CRM | — | yes | Generate an AI image via kie.ai and return its public R2 URL. Use to mint reusable URLs for content blocks (image, gallery), product photos, or any field that takes an image URL — does NOT attach to a post by itself. Costs credits (see list_image_models). On poll timeout the job continues running; pass `jobId` from the response to merchant ai-media APIs to retrieve it later. |
| 23 | Frenchielab94 · Media & Creative | lab94 | Media & Creative | — | yes | Generate a single image from a text prompt through Frenchie. Required: prompt. Optional: style (free-text style direction), size, quality, format, background. stdio mode auto-saves the image to .frenchie/<slug>/generated.<ext>; HTTP mode returns a presigned imageUrl that the agent should download for the user. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.