OpenAI Image MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | debug | info | warn | error | info |
| DEFAULT_MODEL | No | gpt-image-1 / gpt-image-1-mini / gpt-image-2 | gpt-image-2 |
| OPENAI_API_KEY | Yes | OpenAI API key | |
| PROMPT_ENHANCE | No | locally augment short prompts | false |
| SPEND_LOG_PATH | No | append per-call cost records as JSONL | |
| ALLOW_URL_INPUT | No | allow image inputs given as URLs | false |
| CONFIRM_ABOVE_N | No | require confirm:true when generating more than N images | |
| OPENAI_BASE_URL | No | override API base URL | |
| IMAGE_OUTPUT_DIR | No | where images are saved | ~/Pictures/openai-image-mcp |
| DEFAULT_OUTPUT_MODE | No | path | base64 | both | path |
| MAX_COST_PER_CALL_USD | No | reject a call whose estimate exceeds this |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageC | Generate image(s) from a text prompt using OpenAI gpt-image models. |
| edit_imageC | Edit, extend, or compose images with a prompt and optional mask (gpt-image). |
| edit_image_conversationB | Multi-turn iterative image editing via the Responses API (stateful by previous_response_id). |
| image_capabilitiesA | Discover available models, allowed params, size/quality limits, pricing as-of date, and defaults. |
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 4 tools
Each tool targets a distinct image operation: single edit, multi-turn edit, generation from text, and capability discovery. There is no overlap in purpose.
Tool names mix verb_noun (edit_image, generate_image) with noun_noun (image_capabilities) and a longer compound (edit_image_conversation). While all use snake_case, the pattern is inconsistent.
Four tools cover essential image operations without excess. The scope is well-defined for a focused MCP server.
Core image generation and editing workflows are covered, including multi-turn. Missing a dedicated variation tool is a minor gap, but the set is largely complete.