# MCP Kandinsky

> Use this tool when you need to generate high-quality images from text descriptions, and want to control the style, composition, and output size. It solves problems such as creating custom artwork, illustrations, or graphics from textual ideas, and can be used in various contexts like graphic design, advertising, or social media content creation. The tool takes text prompts, styles, and image dimensions as inputs, and produces generated images as output.

Canonical page: https://skillsregistry.net/skills/trashchenkov-mcp-kandinsky  
JSON: https://api.skillsregistry.net/v1/skills/trashchenkov-mcp-kandinsky

## Description

Generates images from text prompts using the Kandinsky neural network API, with support for styles, negative prompts, and configurable image dimensions.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jlnzcniq05)
- **Repository:** <https://github.com/trashchenkov/mcp_kandinsky>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "trashchenkov-mcp-kandinsky"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/trashchenkov-mcp-kandinsky` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/trashchenkov-mcp-kandinsky/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt