# llm-vision

> llm-vision — 1710782766-llm-vision. Use this tool when you need to enable vision capabilities for language models, describing images and extracting text from visual data. It solves problems of image understanding and text extraction for vision-less LLMs, providing a local MCP server interface that takes image inputs and outputs descriptive text. Ideal for use cases requiring image analysis and text extraction, such as data enrichment and content understanding.

Canonical page: https://skillsregistry.net/skills/1710782766-llm-vision  
JSON: https://api.skillsregistry.net/v1/skills/1710782766-llm-vision

## Description

A local MCP server that gives vision to vision-less LLMs by describing images and extracting text via Alibaba DashScope vision models.

## Trust

- **Trust score (0–1):** 0.68
- **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/ee7wcdzugo)
- **Repository:** <https://github.com/1710782766/llm_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": "1710782766-llm-vision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/1710782766-llm-vision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/1710782766-llm-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