@runapi.ai/gpt-image-2-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | No | Your RunAPI API key. Alternatively, write it to ~/.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. |
| edit_imageB | Create a GPT Image 2 task on RunAPI (edit image). Returns a task id, status, and output URLs. |
| text_to_imageB | Create a GPT Image 2 task on RunAPI (text to image). Returns a task id, status, and output URLs. |
| get_taskC | Fetch the current status and latest result payload for a gpt-image-2 task. |
| check_pricingC | Look up RunAPI pricing for the gpt-image-2 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 5 tools
Each tool has a clearly distinct role: login (auth), text_to_image and edit_image (task creation in two distinct modes), get_task (status/result retrieval), and check_pricing (billing lookup). The create-vs-fetch boundary between text_to_image/edit_image and get_task is unambiguous, and the two image modes are clearly separated.
All names use snake_case with a verb_noun or action-verb convention (get_task, edit_image, text_to_image, check_pricing, login). The style is uniform and predictable throughout, with 'login' being the only single-verb name but still in the same casing convention.
Five tools is well-scoped for an image-generation API wrapper: one for auth, two for the two generation modes, one for polling results, and one for pricing. Every tool earns its place with no redundancy or filler.
The core lifecycle (auth → create task → poll result) plus pricing is covered, which is the essential surface for this domain. Minor gaps exist: no way to list or cancel/delete prior tasks, and no logout/credential management, but agents can work around these.