@runapi.ai/flux-kontext-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUNAPI_API_KEY | Yes | 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 Flux Kontext task on RunAPI (text to image). Returns a task id, status, and output URLs. |
| get_taskB | Fetch the current status and latest result payload for a flux-kontext task. |
| check_pricingB | Look up RunAPI pricing for the flux-kontext 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 operation: task creation, task status retrieval, pricing lookup, and authentication. There is no overlap in purpose, so an agent can easily select the correct tool.
Names are mostly snake_case and readable, with get_task and check_pricing following a clear verb_noun pattern. The only minor deviation is login (no underscore), but it does not significantly hinder clarity.
Four tools is reasonable for a focused API wrapper covering generation, status polling, pricing, and auth. It is slightly thin but not problematic for the stated scope.
The server covers task creation, status retrieval, pricing, and authentication, but lacks lifecycle operations like cancel, list, or delete for tasks. Also, despite the 'kontext' model often supporting image editing, only text-to-image is exposed, leaving a notable gap.