# Vision MCP

> Use this tool when you need to analyze and understand images using advanced Vision Language Models. It solves problems such as image classification, object detection, and content understanding, and accepts inputs from URLs or local files with custom prompts. The Vision MCP tool provides outputs in a format compatible with OpenAI APIs, making it ideal for applications requiring image analysis and AI-driven insights.

Canonical page: https://skillsregistry.net/skills/i-richardwang-vision-mcp  
JSON: https://api.skillsregistry.net/v1/skills/i-richardwang-vision-mcp

## Description

Enables image analysis and understanding using Vision Language Models through OpenAI-compatible APIs. Supports analyzing images from URLs or local files with custom prompts.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-04-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/y510dzy6yf)
- **Repository:** <https://github.com/i-richardwang/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": "i-richardwang-vision-mcp"
    }
  }
}
```

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