GPT-Image MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMAGE_MODEL | No | Model to use for image generation (e.g., gpt-image-2, agnes-image-2.0-flash) | |
| IMAGE_PROXY | No | HTTP proxy URL for accessing the API (e.g., http://127.0.0.1:7890) | |
| IMAGE_API_KEY | Yes | API key for the image generation service | |
| IMAGE_API_URL | Yes | The base URL for the image generation API (e.g., https://api.openai.com/v1/images/generations or https://apihub.agnes-ai.com/v1/images/generations) | |
| IMAGE_CONFIG_PATH | No | Path to a JSON configuration file (overrides defaults, but environment variables take precedence) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| text_to_imageC | 根据文本描述生成图片 |
| image_to_imageB | 基于参考图片和文本描述生成新图片 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |