# codex-vision-bridge

> codex-vision-bridge — raven-moonfade-codex-vision-bridge. Use this tool when you need to enhance text-based Codex models with visual capabilities, solving problems such as image description, OCR, element localization, and UI reading. It supports four modes: describe, locate, photo, and ui, providing a versatile interface for various applications. With a simple one-command installation, it integrates seamlessly with git, making it an ideal solution for developers and users alike.

Canonical page: https://skillsregistry.net/skills/raven-moonfade-codex-vision-bridge  
JSON: https://api.skillsregistry.net/v1/skills/raven-moonfade-codex-vision-bridge

## Description

为纯文本 Codex 模型补上看图能力的 MCP 工具：支持 describe（看图描述/OCR）、locate（界面元素定位）、photo（图片内容保真）、ui（界面读屏）四种模式。一条命令安装。

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/raven-moonfade/codex-vision-bridge)

## 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": "raven-moonfade-codex-vision-bridge"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/raven-moonfade-codex-vision-bridge` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/raven-moonfade-codex-vision-bridge/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