openai-image-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | Your OpenAI API key. If not set, the server reads the key from a file named `api_key` in the platform's openai config location (e.g. `~/.config/openai/api_key` on macOS/Linux, `%APPDATA%\openai\api_key` on Windows). | |
| OPENAI_IMAGE_MODEL | No | Default OpenAI image model. | gpt-image-2 |
| OPENAI_IMAGE_OUTPUT_DIR | No | Folder for images saved without a full `output_path`. | your Pictures folder |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate an image with OpenAI and save it to disk. Returns the saved file path. QUALITY - choose carefully, higher quality costs much more:
size: 1024x1024 square, 1536x1024 landscape (hero banners), 1024x1536 portrait. background: "transparent" for logos/icons/stickers (needs png or webp). output_path: where to save, ideally an absolute path inside the user's project, e.g. "/Users/me/site/images/hero.png" or "C:\Users\me\site\hero.png". ~ and environment variables are expanded. A folder gets an auto-named file; a relative path is saved inside the default folder. If omitted, saves to the user's Pictures folder. model: override the default model (normally leave empty). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possible confusion with a sibling tool; its purpose (generate an image and save it to disk) is unmistakable. The extensive parameter documentation further removes any ambiguity about behavior.
The single tool name 'generate_image' follows a clean verb_noun snake_case convention. With one name there are no competing conventions or style inconsistencies to flag.
A one-tool server is on the thin side by the rubric's standards, though the narrow scope (text-to-image generation) makes a single entry point defensible. It borders on under-scoped: there is no separate tool for listing, inspecting, or iterating on generated assets.
For a generate-and-save image workflow, the core operation is fully covered with useful knobs (size, quality, background, output_path, model). Minor gaps remain, such as no variation/edit/regenerate tool or way to enumerate previously generated files, but an agent can work around these by calling the tool again with a known path.