# MCP Kandinsky

> Use this tool when you need to generate images from text prompts, solving problems like creating art, designing concepts, or visualizing ideas. It takes text inputs and produces image outputs via the Kandinsky AI API. Ideal for use cases where creative visualization or automated image generation is required, such as art, design, or marketing applications.

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

## Description

MCP server that generates images from text prompts using the Kandinsky AI via official API.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/h7lr0r8cs3)
- **Repository:** <https://github.com/ai-forever/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": "ai-forever-mcp-kandinsky"
    }
  }
}
```

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