# KIMI AI

> Use this tool when you need to integrate AI capabilities into your workflow, such as multilingual text generation and image analysis, through standardized API endpoints. It solves problems like custom AI service integration and provides inputs like text and image data, with outputs including generated text and image analysis results. Ideal for use cases where MCP-compatible applications require access to advanced AI services, including text and vision tasks.

Canonical page: https://skillsregistry.net/skills/kimi-ai  
JSON: https://api.skillsregistry.net/v1/skills/kimi-ai

## Description

MCP server implementation that provides AI assistants with access to KIMI AI services through OpenAI-compatible API endpoints, featuring both text generation and vision capabilities using Qwen models (Qwen2.5-72B-Instruct for text and Qwen2.5-VL-72B-Instruct for vision tasks). The implementation includes a FastAPI-based server architecture with MCP protocol support, custom detection services, and a web-based client interface for testing interactions. Built with configurable API endpoints and model selection, it serves users who want to integrate KIMI's AI capabilities into their workflows through standardized MCP tooling, supporting use cases like multilingual text generation, image analysis, and custom AI service integration with existing MCP-compatible applications.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/kimi-ai)
- **Repository:** <https://github.com/adamleen/mcp-kimi>

## 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": "kimi-ai"
    }
  }
}
```

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