Skip to content
Clipia.
Home
What are we creating?

Pick a mode — Studio opens with the right prompt ready

All templates
Video
Text → videoDescribe a scene and get a clipImage → videoBring a frame to life with motionVideo templatesReady-made scenes and styles
Images
Text → imageGenerate an image from a promptEditModify an existing photoImage templatesReady-made product shots and art
BlogPricingFor Partners
Sign In
  • Home

  • Create Video

  • Create Image

  • Templates

  • My Works

  • Models

  • Support

Clipia.

Think differently — create the impossible.

Product

  • Create Image
  • Create Video
  • AI Models
  • Video Models
  • Image Models
  • Guides
  • Model Rankings
  • Balance

Support

  • About
  • Contact Us
  • Telegram Support

Legal

  • Terms of Service
  • Privacy Policy
  • Payment information
  • Cross-Border Transfers
  • Acceptable Use
  • Cookie Policy
  • Content License
  • Partner Agreement
Terms of Service·Privacy Policy·Cookie Policy·Acceptable Use
© 2026 Clipia.ai. All rights reserved.
  1. Home/
  2. MCP/
  3. generate_image
MCP tool · generate_image

Generate images right inside the AI-agent chat

Describe the shot in words — the agent calls generate_image, waits for the result, and shows the image right in the chat. You can pass references for editing (image-to-image).

generate_image is a tool of the Clipia MCP server for generating an image from text or editing by references. The agent (Claude, ChatGPT, Cursor) calls it right in the conversation: you give a prompt and optionally aspect ratio, resolution, and up to four reference images. The tool waits for the result for up to 25 seconds and usually returns the ready image together with a compact preview, so the agent can «see» the result and refine it.

Tool parameters

ParameterTypeReq.Description
promptstringyesDescription of the shot (RU or EN)
modelstring—Model slug; defaults to the agent’s pick
aspect_ratiostring—e.g. 1:1, 16:9, 9:16
resolutionstring—1k / 2k / 4k
num_imagesint (1–4)—How many variants to generate
image_urlsstring[] (≤4)—HTTPS references → image-to-image mode
include_previewbool—Return an inline preview (default yes)

Request example (MCP tools/call)

{
  "name": "generate_image",
  "arguments": {
    "prompt": "тёмный неоновый постер кофейни, крупный план чашки, пар",
    "aspect_ratio": "9:16",
    "resolution": "2k"
  }
}

Response example

{
  "request_id": "f1c3...­9ab",
  "status": "COMPLETED",
  "model": "nano-banana-2",
  "cost_credits": 1,
  "output": {
    "images": [{
      "url": "https://media.clipia.ai/.../preview.webp",
      "original_url": "https://media.clipia.ai/.../original.png"
    }]
  }
}

Reference-based editing

Pass image_urls and the same tool works in image-to-image mode: background swap, styling, edits.

Preview right in the chat

The agent gets a compact preview and can assess the shot and request an edit at once — a vision loop with no tab switching.

No-charge sandbox

With a clipia_test_* key the tool returns an instant mock — debug the integration without spending credits.

Connect in a minute

claude mcp add --transport http clipia https://api.clipia.ai/mcp \
  --header "Authorization: Bearer clipia_live_XXXX"

For claude.ai and ChatGPT no key is needed — sign in with your account. Create a key in Clipia settings.

Pricing

The credit cost is returned in every response (cost_credits) — no hidden MCP markup, the same balance as on the site.

FAQ

Can I prompt in Russian?

Yes, prompt accepts Russian and English text.

How do I edit instead of generating from scratch?

Pass up to 4 HTTPS links in image_urls — image-to-image mode turns on.

How much does one image cost?

The credit cost is in every response (cost_credits) and depends on the model and resolution.

Get an API keyAll MCP tools

Related scenarios: Generate video right inside the AI-agent chat · 3500+ ready prompts right in the chat

Text-to-image in Claude via MCP — Clipia