# multimodal-proxy

> Use this tool when you need to enhance text-based models with multimodal capabilities, such as image, video, and audio analysis. It solves problems like limited contextual understanding and lack of multimedia support by outsourcing analysis to external multimodal models and returning text-based results. Ideal for applications requiring comprehensive media analysis and text-based output.

Canonical page: https://skillsregistry.net/skills/macgaf-multimodal-proxy-plugin  
JSON: https://api.skillsregistry.net/v1/skills/macgaf-multimodal-proxy-plugin

## Description

为纯文本主模型提供多模态能力的MCP服务器，通过外包图像、视频和音频分析给外部多模态模型并回填文字结果。

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/b2my4yoyt1)
- **Repository:** <https://github.com/macgaf/multimodal-proxy-plugin>

## 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": "macgaf-multimodal-proxy-plugin"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/macgaf-multimodal-proxy-plugin` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/macgaf-multimodal-proxy-plugin/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