imagen-mcp
This server provides OpenAI-backed image generation and editing through two MCP tools.
generate_image: Create images from text prompts with configurable model (flare/sunburst), size/aspect ratio, quality, background, format (png/jpeg/webp), compression, variations, and output path/name.edit_image: Edit, restyle, or combine 1–16 reference images using a prompt, optional mask, andinput_fidelitycontrol; same shared output options.Both tools save files to disk and return file paths, model, size, and token usage.
The provided schema exposes only these OpenAI tools; Krea tools from the README are not present.
Provides image generation and editing through OpenAI's GPT Image 2.5 models, supporting customizable sizes, aspect ratios, quality tiers, background transparency, inpainting masks, and multiple output formats.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@imagen-mcp Generate a 3:2 image of a fluffy corgi puppy on a beach, photorealistic"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
imagen-mcp
Minimal MCP server for OpenAI GPT Image 2.6 and Krea 3. Generate and edit tools for each provider.
Provider | Tools | Models |
OpenAI |
|
|
Krea |
| Krea 3: fast, instruction-following editor. Early-access beta. |
The server registers a provider's tools only when that provider's API key is set.
Setup
Install from npm:
npm install -g @falldownthesystem/imagen-mcpOr build from source:
npm install
npm run buildSet one or both API keys in the environment, or put them in a .env file next to package.json:
OPENAI_API_KEY: enables the OpenAI tools.KREA_API_KEY: enables the Krea tools. Create a token at krea.ai/settings/api-tokens. The Krea 3 API is in early access; only workspaces in the beta can call it. Request access at sales@krea.ai.
Optional environment variables:
IMAGEN_OUTPUT_DIR: default directory for saved images (default./output).IMAGEN_DEFAULT_MODEL:flareorsunburst(defaultflare).
Related MCP server: MCP OpenAI Image Generation Server
Client config
Claude Code (.mcp.json) or Claude Desktop, using the npm package:
{
"mcpServers": {
"imagen": {
"command": "npx",
"args": ["-y", "@falldownthesystem/imagen-mcp"],
"env": {
"OPENAI_API_KEY": "sk-...",
"KREA_API_KEY": "...",
"IMAGEN_OUTPUT_DIR": "C:/Users/me/Pictures/imagen"
}
}
}
}Or with a local build, use "command": "node" and "args": ["path/to/imagen-mcp/dist/index.js"].
Claude Code one-liner:
claude mcp add imagen -e OPENAI_API_KEY=sk-... -e KREA_API_KEY=... -- npx -y @falldownthesystem/imagen-mcpOpenAI tools
generate_image
Text to image, animated GIF, or SVG. Required: prompt.
Option | Values | Default | Notes |
|
|
| Also sets the file extension. |
| 2 to 16 | 9 |
|
| 20 to 2000 | 200 |
|
|
|
| OpenAI content filter strictness. |
edit_image
Reference images to image. Required: prompt, images. The model regenerates the whole picture guided by the references and the prompt. Without a mask or markup, the prompt alone decides what changes. Output is png, jpeg, or webp; the edit endpoint does not make GIF or SVG.
Option | Values | Default | Notes |
| 1 to 16 file paths | required |
|
| file path | none | PNG with an alpha channel, same width and height as the first image. Fully transparent pixels mark the region the model may repaint; opaque pixels mark what to keep. Use for inpainting one area or filling an extended canvas. It is guidance, not a hard pixel lock. Cannot be combined with |
| file path | none | Transparent PNG annotation layer, same width and height as the first image, at most 50 MB. Draw circles, arrows, or scribbles where the change goes, and say in the prompt what to change and to remove the marks. Applies to the first image; other images stay references. Cannot be combined with |
There is no input_fidelity option. The GPT Image 2.6 models always process reference images at high fidelity, and the API rejects the parameter. Faces, logos, text, and textures from the references are preserved by default.
Shared options
Only the options you set are sent to the API. The default column shows what applies when an option is omitted.
Option | Values | Default | Notes |
| text, up to 32000 chars | required | |
|
|
|
|
|
|
| Custom sizes: multiples of 16, ratio 1:3 to 3:1, long edge up to 3840. Overrides |
|
| none | Combined with |
| 256 to 3840 | 1536 | Only used with |
|
|
| Higher tiers add detail and cost more output tokens. |
|
|
| How much the model plans the scene before it renders. Separate from |
|
|
|
|
|
|
| Also sets the file extension. |
| 0 to 100 | 100 |
|
| 1 to 10 | 1 | Number of separate variations generated from the same prompt in one call. Each costs its own output tokens. |
| directory path |
| Relative to the server working directory. |
| base name without extension | timestamp plus a slug of the prompt | With |
| boolean |
| Also return each image inline as MCP image content, so the client shows it and the model can inspect it. Adds about 1.4 MB of context per 1024x1024 png. SVG files are never returned inline. The file is saved to disk either way. |
The result lists the saved file paths, the model, the size, and token usage.
Krea tools
Both tools call POST /generate/image/krea/krea-3, poll the job every 2 seconds, and download the result. A job that does not finish in 5 minutes, or a tool call that the client cancels, is cancelled on Krea. Failed and cancelled jobs are not billed.
krea_generate_image
Text to image. Required: prompt.
krea_edit_image
Reference images to image. Required: prompt, images. Write the prompt as an instruction: lead with the change, then add one sentence about what stays the same. With several references, name each one by what it shows, for example "Put the sneaker from the second image on the person in the first image."
Option | Values | Default | Notes |
| 1 to 8 local paths or | required | Local files ( |
| boolean |
|
|
There is no mask option. Krea 3 decides the edit region from the prompt.
Shared Krea options
Only the options you set are sent, except thinking_mode and resolution, which are always sent with their defaults.
Option | Values | Default | Notes |
| text | required | |
|
|
| How much Krea 3 plans before it generates. |
|
|
| Output canvas size. 2K is the native resolution. |
|
| none | Omit for automatic framing. |
| text, up to 1024 chars | none | What to avoid. |
| integer | random | With |
| 1 to 4 | 1 | Each variation is a separate job, billed separately. If some jobs fail, the finished images are still saved and the failures are listed in |
| Same as the OpenAI tools. |
Pricing per image:
Component | 1K output | 2K output |
Base price | $0.03 | $0.06 |
Each 1K reference image | +$0.02 | +$0.02 |
Each 2K reference image | +$0.07 | +$0.07 |
| +$0.02 | +$0.02 |
The result lists the saved file paths, the model, the resolution, the aspect ratio, the thinking mode, and the Krea job IDs.
Available Tools
2 toolsedit_imageEdit imageA
Edit, restyle, or combine 1-16 reference images with a text prompt using OpenAI GPT Image 2.5. The whole picture is regenerated; without a mask the prompt decides what changes. Saves files to disk and returns paths and token usage.
Inputs: images (required), prompt (required), n, mask, +12 more. Returns: size, files, model, usage
generate_imageGenerate imageA
Generate images from a text prompt with OpenAI GPT Image 2.5. Saves files to disk and returns paths and token usage.
Inputs: prompt (required), n, size, model, +10 more. Returns: size, files, model, usage
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
generate_image and edit_image are clearly separated by input and intent: one creates a new image from a prompt, the other modifies or combines existing reference images. There is no meaningful scenario where an agent would confuse which tool to call.
Both tool names use the same underscore-separated verb_noun pattern. The naming is consistent and immediately communicates the action and object.
The server exposes only two tools, which is slightly lean relative to the typical 3-15 tool range. However, the count matches the narrow image-generation/editing scope and omits unnecessary extras.
The two tools cover the core lifecycle of the domain: creating an image and editing existing images. Outputs are saved and paths returned, so an agent can continue working with the results.
Maintenance
Related MCP Connectors
Edit images over MCP with object removal, background removal, and guided generative edits.
Create and manage AI image and video generations through Quriov's fixed public MCP tools.
Generate images and videos with Seedance, Veo, Wan, Grok, GPT-Image and Nano Banana via one MCP.
AI video, image and audio generation with 140+ AI models from any MCP agent
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides tools for generating and editing images using OpenAI's gpt-image-1 model via an MCP interface, enabling AI assistants to create and modify images based on text prompts.15Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to generate and edit images through OpenAI's DALL-E models via MCP tools. Supports text-to-image generation and image-to-image editing with configurable parameters for size, quality, and style.-
- FlicenseNot gradedqualityDmaintenanceEnables AI-powered image generation using Google's Gemini 2.5 Flash Image Preview model, supporting text-to-image and image-to-image generation through the MCP interface.-
- AlicenseNot gradedqualityDmaintenanceGenerates and edits images using OpenAI image models via MCP tools.MIT