kokon
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QLS_MCP_ALLOWED_DIRS | No | Folders the MCP server is allowed to read from and write to, in addition to the project folder and Kokon's output folder. Multiple folders are separated by semicolons. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate an image from a text prompt with the local Qwen-Image 2.1 model. Dimensions are chosen automatically (aspect ratio can be inferred from the prompt, e.g. '16:9 hero image') unless width/height or aspect_ratio are given. Returns the absolute path of the saved PNG. Runs fully offline; typically 45 s–4 min. |
| edit_imageA | Edit an existing image with a natural-language instruction (e.g. 'make the background nighttime, keep the foreground unchanged'). Preserves the input's width, height and aspect ratio by default. The input file is never overwritten. |
| edit_imagesA | Create an image from several reference images (up to 10) and an instruction. Order matters: refer to them as image 1, image 2, ... in the prompt. The output follows image 1's aspect ratio unless width/height or aspect_ratio are given. |
| outpaint_imageA | Extend an image beyond its borders. Give the expansion per side in pixels or percent; the canvas, mask and model-aligned sizes are built automatically and the original pixels are preserved exactly. |
| inpaint_imageA | Change only the masked area of an image (mask: white = change, black = keep): edit it, remove what is there, replace it, or add something inside it. The model is shown the area marked on a copy of the image; pixels outside the mask are preserved exactly. |
| upscale_imageA | Enlarge an image (default 2x, or to a width/height up to 8192 px). Runs the upscaler model chosen in Kokon (Superscale-SP by default; seconds on a PC GPU, longer on a Mac; adds no new content). Saves a new file; the input is never overwritten. |
| get_image_infoC | Width, height, aspect ratio, file type and, for images made by Kokon, the generation metadata (prompt, seed, model, steps...). |
| get_generator_statusB | Whether the local inference server is running and the model loaded, GPU and VRAM, the active job and the queue. |
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 8 tools
Most tools have clearly distinct purposes (outpaint, inpaint, upscale, info, status), and descriptions clarify boundaries between inpainting and editing. However, edit_image vs edit_images differ by a single character while doing conceptually different things (single-image instruction edit vs multi-reference generation), which is a real misselection hazard.
Every tool follows a consistent snake_case verb_noun pattern (generate_image, edit_image, outpaint_image, inpaint_image, upscale_image, get_image_info, get_generator_status). The convention is predictable throughout with no style mixing.
Eight tools is well-scoped for an offline image generation/editing server; each operation (generate, edit, multi-ref compose, outpaint, inpaint, upscale, inspect, status) earns its place without redundancy.
The surface covers the full generation-to-post-processing lifecycle plus system status, which is strong for the domain. Minor gaps remain: no way to list, delete, or manage saved output files, which an agent may eventually need.