# mcp-qwen-omni

> mcp-qwen-omni — zk-b612-mcp-qwen-omni. Use this tool when you need to integrate multi-modal AI capabilities, such as image, audio, and video understanding, into your AI assistant. It solves problems of limited interaction modes by providing a seamless integration of various modalities through the Model Context Protocol (MCP). With inputs of multimedia data and outputs of synthesized responses, use mcp-qwen-omni to upgrade your AI to a versatile multi-modal interactant.

Canonical page: https://skillsregistry.net/skills/zk-b612-mcp-qwen-omni  
JSON: https://api.skillsregistry.net/v1/skills/zk-b612-mcp-qwen-omni

## Description

这是一个基于通义千问（Qwen-Omni）实现的多模态 AI 服务，通过 Model Context Protocol (MCP) 将其强大的看图、听音、语音合成及视频理解能力无缝集成到支持MCP服务的 AI 助手（如 Claude, Cursor）中。让你的 AI 瞬间升级为全能型选手，轻松实现多模态交互！

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/zk-b612/mcp-qwen-omni)

## 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": "zk-b612-mcp-qwen-omni"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zk-b612-mcp-qwen-omni` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zk-b612-mcp-qwen-omni/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