claude-openai-image-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API key. Required only when IMAGE_MCP_PROVIDER is 'openai'. | |
| IMAGE_MCP_PROVIDER | No | Provider: 'mock' (offline) or 'openai' (requires API key) | mock |
| OPENAI_IMAGE_MODEL | No | Server-owned model name. Not settable by clients. | gpt-image-2 |
| IMAGE_MCP_TIMEOUT_MS | No | Per-request upstream timeout in milliseconds. | 60000 |
| IMAGE_MCP_MAX_RETRIES | No | Maximum number of transient retries. | 0 |
| IMAGE_MCP_DEFAULT_SIZE | No | Default size when client omits it. Defaults to first allowed size. | |
| IMAGE_MCP_ALLOWED_SIZES | No | Comma-separated list of allowed sizes (e.g., '1024x1024,1536x1024'). | 1024x1024,1536x1024,1024x1536 |
| IMAGE_MCP_DEFAULT_FORMAT | No | Default output format when client omits it. Defaults to first allowed format. | |
| IMAGE_MCP_ALLOWED_FORMATS | No | Comma-separated list of allowed output formats (e.g., 'png,webp,jpeg'). | png,webp,jpeg |
| IMAGE_MCP_DEFAULT_QUALITY | No | Default quality when client omits it. Defaults to first allowed quality. | |
| IMAGE_MCP_MAX_CONCURRENCY | No | Maximum concurrent generations. | 1 |
| IMAGE_MCP_MAX_PROMPT_CHARS | No | Maximum number of characters for the prompt. | 2000 |
| IMAGE_MCP_ALLOWED_QUALITIES | No | Comma-separated list of allowed qualities ('low','medium', etc.). | low,medium |
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_imageA | Generate an image from a text prompt using the configured OpenAI image model. Returns an image (base64) plus metadata. size/quality/output_format are optional and restricted to the server allowlist; the server picks the model. |
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
Only one tool exists, so there is no possibility of confusion or overlap.
With a single tool, naming consistency is perfect; the name 'generate_image' clearly describes its action.
The one tool matches the server's narrow purpose of generating images from prompts; no additional tools are needed.
The tool covers the core functionality of generating images. Minor gaps like listing available models or presets could be added, but the current surface is adequate.