# jl-image-vison

> jl-image-vison — liugangnhm-jl-image-vison-mcp. Use this tool when you need to analyze and understand visual layouts, UI designs, and HTML pages, as it provides structured descriptions of layout hierarchy, components, text, interactions, and accessibility notes. It solves problems related to image understanding, UI design analysis, and accessibility evaluation, taking in visual inputs and returning detailed outputs. Ideal for use cases where automated image analysis and description are required, such as quality assurance, design optimization, and accessibility testing.

Canonical page: https://skillsregistry.net/skills/liugangnhm-jl-image-vison-mcp  
JSON: https://api.skillsregistry.net/v1/skills/liugangnhm-jl-image-vison-mcp

## Description

MCP server for image understanding that analyzes UI designs, HTML pages, and visual layouts using Agnes 2.0 Flash, returning structured descriptions with layout hierarchy, components, text, interactions, and accessibility notes.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **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/wge4kqlpvx)
- **Repository:** <https://github.com/liugangnhm/jl_image-vison-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": "liugangnhm-jl-image-vison-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/liugangnhm-jl-image-vison-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/liugangnhm-jl-image-vison-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