@runapi.ai/gpt-4o-image-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | No | Your RunAPI API key. Can also be stored in ~/.config/runapi/config.json. |
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
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| loginA | Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json. |
| text_to_imageB | Create a GPT-4o Image task on RunAPI (text to image). Returns a task id, status, and output URLs. |
| get_taskA | Fetch the current status and latest result payload for a gpt-4o-image task. |
| check_pricingC | Look up RunAPI pricing for the gpt-4o-image model line. |
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 action: text_to_image creates a generation task, get_task polls status/result, check_pricing is a read-only info lookup, and login handles auth. There is no overlap and an agent can trivially tell them apart.
text_to_image, get_task, and check_pricing roughly follow a verb/noun style, while login is a bare verb. Mostly consistent with one minor deviation.
Four tools is a reasonable, well-scoped set for a single-model image service: one generation, one polling, plus pricing and auth support. It is slightly thin but nothing is redundant.
The core create-and-poll workflow is covered, but the surface lacks common image operations such as image-to-image/editing, variations, listing tasks, or cancellation. These are notable gaps for a GPT-4o image line.