# deepseek-vision

> deepseek-vision — sunlianwang-deepseek-vision. Use this tool when you need to enable text-only large language models (LLMs) to understand and interpret visual data, such as images, audio, and video. Deepseek-vision solves the problem of limited perception in LLMs by providing a multimodal interface that returns text descriptions of visual inputs. It takes in multimedia files and outputs text, allowing LLMs to reason and respond to visual data in various applications.

Canonical page: https://skillsregistry.net/skills/sunlianwang-deepseek-vision  
JSON: https://api.skillsregistry.net/v1/skills/sunlianwang-deepseek-vision

## Description

MCP server that gives text-only LLMs vision capabilities by using a free multimodal model to perceive images, audio, and video, returning text for the main model to reason with.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hvedopdld6)
- **Repository:** <https://github.com/Sunlianwang/deepseek-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": "sunlianwang-deepseek-vision"
    }
  }
}
```

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