GPT Image MCP
by Yularzhi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMAGE_DIR | No | Image storage directory | |
| LOG_LEVEL | No | Logging level, default INFO | |
| PUBLIC_URL | No | Public base URL for returned image links | |
| MAX_MASK_MB | No | Max size for masks, default 4 | |
| MCP_API_KEY | No | Bearer token required for /mcp/ and /images/* | |
| MAX_UPLOAD_MB | No | Max size for uploaded images, default 50 | |
| OPENAI_API_KEY | Yes | OpenAI API key | |
| MAX_IMAGE_EDGE_PX | No | Max image edge length, default 8192 | |
| IMAGE_RETENTION_DAYS | No | Cleanup retention window, default 7 | |
| OPENAI_RETRY_ATTEMPTS | No | Retry count for OpenAI image calls, default 3 | |
| REQUEST_TIMEOUT_SECONDS | No | Timeout for remote image downloads, default 60 | |
| CLEANUP_INTERVAL_SECONDS | No | Cleanup interval, default 86400 | |
| OPENAI_RETRY_BASE_DELAY_SECONDS | No | Retry backoff base, default 0.75 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |