# dsh-vision

> dsh-vision — smjda0719-dsh-vision. Use this tool when you need to analyze visual data, such as images, videos, and documents, to extract insights and understand their content. The dsh-vision tool provides vision understanding capabilities, including image QA, OCR, and document understanding, through OpenAI-compatible endpoints. It is ideal for applications requiring automated visual data processing, such as text extraction, object detection, and content analysis.

Canonical page: https://skillsregistry.net/skills/smjda0719-dsh-vision  
JSON: https://api.skillsregistry.net/v1/skills/smjda0719-dsh-vision

## Description

An MCP server providing vision understanding tools (image QA, OCR, video and document understanding) via OpenAI-compatible endpoints, defaulting to Zhipu GLM vision models.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gas4i9d4e2)
- **Repository:** <https://github.com/smjda0719/dsh-vision>

## 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": "smjda0719-dsh-vision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/smjda0719-dsh-vision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/smjda0719-dsh-vision/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