# MiniCPM Vision MCP

> Use this tool when you need to enable local visual capabilities for AI assistants like DeepSeek and Claude Desktop, supporting image description and video frame analysis while keeping data on-device. It solves problems related to visual data analysis and processing, providing a secure and private solution. The tool takes images and video frames as input and outputs descriptive text, making it ideal for use cases where data privacy is a concern.

Canonical page: https://skillsregistry.net/skills/wjh1547485653-max-minicpm-vision-mcp  
JSON: https://api.skillsregistry.net/v1/skills/wjh1547485653-max-minicpm-vision-mcp

## Description

为DeepSeek、Claude Desktop等AI助手提供本地视觉能力，支持图片描述和视频帧分析，数据不出机。

## Trust

- **Trust score (0–1):** 0.69
- **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/dw5cmbez0l)
- **Repository:** <https://github.com/wjh1547485653-max/minicpm-vision-mcp>

## 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": "wjh1547485653-max-minicpm-vision-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wjh1547485653-max-minicpm-vision-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wjh1547485653-max-minicpm-vision-mcp/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