RunningHub Image Gen MCP Plugin
# RunningHub Image Gen MCP Plugin
A Codex MCP plugin for generating images via RunningHub's seedream-v5-lite model.
## Prerequisites
- Python >= 3.11
- [uv](https://docs.astral.sh/uv/) package manager
- A RunningHub API key (set as `RUNNINGHUB_API_KEY`)
## Install
```bash
cd work/runninghub-image-gen
uv sync
```
## Usage
### Environment variable
```bash
export RUNNINGHUB_API_KEY=your-api-key-here
```
### Tools
| Tool | Description |
|------|-------------|
| `text_to_image` | Submit a text-to-image task, returns taskId |
| `query_task` | Poll task status/results by taskId |
| `run_text_to_image` | Submit + poll until complete |
### Available parameters
- `prompt` (required) — Text description of the image
- `width` / `height` — Image dimensions in pixels
- `max_images` — Number of images to generate
- `sequential_image_generation` — "enabled" or "disabled"
- `tools_type` — e.g. "web_search"
### Running standalone
```bash
RUNNINGHUB_API_KEY=your-key uv run runninghub-image-gen
```
## API
- Submit: `POST /openapi/v2/seedream-v5-lite/text-to-image`
- Query: `POST /openapi/v2/query`
TDQS
Scored across 3 tools
The tools have clear descriptions but overlap: text_to_image and run_text_to_image both submit tasks, with run_text_to_image combining submission and polling. An agent might be uncertain which to use, though the descriptions help distinguish asynchronous vs synchronous workflows.
Naming is mixed: 'query_task' and 'run_text_to_image' follow a verb_noun pattern, but 'text_to_image' lacks a verb and reads as a noun phrase. The patterns are inconsistent, reducing predictability.
Three tools is minimal but reasonable for a focused plugin covering async submission, polling, and a combined sync call. It is slightly under the typical range but not problematic.
Covers the core workflow of submitting and retrieving image generation tasks, but lacks obvious operations like canceling tasks or listing all tasks. This leaves notable gaps for a full lifecycle.