mcp-simple-image
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., "@mcp-simple-imagegenerate an image of a sunset over the ocean, 1024x1024"
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.
mcp-simple-image
A simple MCP (Model Context Protocol) tool for generating images from text prompts using StepFun-compatible APIs. Configurable endpoint, API key, and model.
Features
Simple MCP tool:
simple_imageFully configurable: API base URL, API key, model name
Zero external dependencies (pure Python stdlib)
Works with StepFun
step_planAPI and compatible endpoints
Related MCP server: nano-banana-mcp
Installation
git clone https://github.com/bauerelizabeth07139/mcp-simple-image.git
cd mcp-simple-imageConfiguration
Set your API key via environment variables (recommended) or a config.json file.
Option 1: Environment Variables
STEP_API_KEY=your_api_key_here
STEP_API_BASE=https://api.stepfun.com/step_plan/v1
STEP_MODEL=step-image-edit-2Option 2: Config File
Copy config.example.json to config.json and fill in your values:
{
"api_key": "your_api_key_here",
"api_base": "https://api.stepfun.com/step_plan/v1",
"model": "step-image-edit-2",
"size": "1024x1024",
"n": 1
}Usage
Run the MCP server
python server.pyUse with opencode
Add to your opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"simple-image": {
"type": "local",
"command": [
"python",
"/path/to/mcp-simple-image/server.py"
],
"enabled": true,
"environment": {
"STEP_API_KEY": "your_key_here",
"STEP_API_BASE": "https://api.stepfun.com/step_plan/v1",
"STEP_MODEL": "step-image-edit-2"
}
}
}
}Or if you use a config.json file in the same directory:
{
"mcp": {
"simple-image": {
"type": "local",
"command": ["python", "/path/to/mcp-simple-image/server.py"],
"enabled": true
}
}
}Tool: simple_image
Parameter | Type | Required | Default | Description |
| string | Yes | - | Text description of the image |
| string | No | (from config) | Model name |
| string | No | (from config) | Image dimensions, e.g. |
| integer | No | (from config) | Number of images (1-4) |
Example prompt in opencode:
Use simple_image to generate: a cute cat astronaut floating in space, cinematic lighting, 8KTesting
# Direct API test
python test_api.py
# MCP protocol test
python test_mcp.pyLicense
MIT
Related MCP Connectors
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Generate images with your own ChatGPT subscription (Plus, Pro or Team), without spending API credits
Generate images with any major model — one API key, one prepaid balance, one MCP.
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
1611
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables users to generate images from text prompts using Replicate's model, with configurable parameters and full MCP protocol compliance.1123-
- FlicenseNot gradedqualityDmaintenanceGenerates images using Google's Gemini model, with options to save to file or return as base64 data URL.-
- AlicenseNot gradedqualityBmaintenanceProvides image generation tools powered by OpenRouter, running on Cloudflare Workers.26 npmMIT
- FlicenseNot gradedqualityBmaintenanceGenerates images and videos from text prompts using Cloudflare Workers AI and Google Gemini models.-