# dsh-vision-mcp

> dsh-vision-mcp — moton16-dsh-vision-mcp. Use this tool when you need to enable text-only Large Language Models (LLMs) to understand images by converting them into text descriptions. It solves the problem of limited input modalities for LLMs, allowing them to process visual data through text-based interfaces. The dsh-vision-mcp tool takes images as input and outputs text descriptions, providing a fallback mechanism across multiple vision API providers for reliable functionality.

Canonical page: https://skillsregistry.net/skills/moton16-dsh-vision-mcp  
JSON: https://api.skillsregistry.net/v1/skills/moton16-dsh-vision-mcp

## Description

Zero-dependency MCP server that equips text-only LLMs (e.g., DeepSeek) with vision by converting images to text descriptions via OpenAI-compatible vision APIs, exposing an img2text tool with multi-provider fallback.

## Trust

- **Trust score (0–1):** 0.67
- **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/jkbkc2wekd)
- **Repository:** <https://github.com/moton16/dsh-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": "moton16-dsh-vision-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/moton16-dsh-vision-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/moton16-dsh-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