generate_image
Generate a new image from a text prompt or edit an existing image using inputImagePath. Saves the result and returns a file resource.
LABSCO SUMMARY
One tool with a dozen arguments: the controls that normally live in an image UI arrive as parameters.
Creating and editing share a single entry point, and the input image path is what switches between them, so there is no second tool to learn and no separate edit flow. The prompt optimizer is doing real work here — a short brief becomes a described scene before the image model sees it — and it is the first thing to turn off when the exact wording matters. What the server does not do is anything after the save: no listing, no deletion, no reopening an earlier result, so the file name you choose is the handle you keep.
What it is
A single-tool image server in front of Gemini, OpenAI or BytePlus Seedream, writing every result into an output directory and handing it back as a file resource.
What you get
- Text-to-image and image editing through one call: a prompt alone creates, a prompt plus an input image path edits the file at that path
- Prompt enhancement that fills in subject, lighting, camera and palette detail before the image model sees it — switched off with SKIP_PROMPT_ENHANCEMENT when the wording has to survive unchanged
- Three quality presets — fast, balanced and quality — each mapped to a different model route, set as a default or per call
- Framing decided before generation: aspect ratios from square to ultra-wide and ultra-tall, resolution up to 4K depending on provider and route, and the saved file's name
- Character consistency for follow-up images that keep the same subject, and blending for merging several inputs into one result
- Google Search grounding and world knowledge on the Gemini provider, for pictures that have to match something real
- The provider chosen per request as well as per server, so one configuration can serve all three
Requirements
Node.js 22 or newer, and a key for whichever provider you use: GEMINI_API_KEY by default, OPENAI_API_KEY with IMAGE_PROVIDER=openai — which needs a verified OpenAI organization — or ARK_API_KEY for Seedream. IMAGE_OUTPUT_DIR must be an absolute path and is created if missing; without it, results land in ./output. The server starts without any key, and the error on the first call names the variable to set. MIT.
Setup effort
One command plus a key — npx -y mcp-image, then supply credentials
USE CASES
01
Getting a first visual out of a written brief
Describe the picture, set the aspect ratio and size for where it has to fit, and name the file so it can be found again.
02
Keeping one character across a set of images
Point at the image you already accepted and ask for character consistency, so the next image continues the same subject rather than inventing a new one.
03
Iterating cheaply, then rendering the final one properly
Work at the fast preset while the composition is still moving, and switch that one call to the quality preset when it is the deliverable.
04
Making a picture of something real
Turn on search grounding or world knowledge so a landmark, a product or a historical subject is depicted from outside detail rather than from the prompt text alone.
1 tool
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool when we connected. Editing, character consistency, 4K and Google Search grounding all run through generate_image parameters such as inputImagePath, not separate tools.
Requires
- npx on PATH
- Node.js 22 or later
- GEMINI_API_KEY in your environment
Where it runs
All 3 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y mcp-imageMCP Clients
Codex
CODEX · TOML
[mcp_servers.mcp-image]
command = "npx"
args = ["-y", "mcp-image"]
[mcp_servers.mcp-image.env]
GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>"
IMAGE_OUTPUT_DIR = "<YOUR_IMAGE_OUTPUT_DIR>"Cursor
CURSOR · JSON
{
"mcpServers": {
"mcp-image": {
"command": "npx",
"args": [
"-y",
"mcp-image"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"IMAGE_OUTPUT_DIR": "<YOUR_IMAGE_OUTPUT_DIR>"
}
}
}
}Claude Code
CLAUDE CODE · TERMINAL
claude mcp add mcp-image --env GEMINI_API_KEY=<YOUR_GEMINI_API_KEY> --env IMAGE_OUTPUT_DIR=<YOUR_IMAGE_OUTPUT_DIR> -- npx -y mcp-image
