# mcp-vision

> mcp-vision — kobexi26-mcp-vision. Use this tool when you need to enable image recognition capabilities for models lacking visual abilities, or require picture description and text extraction functionalities. The mcp-vision tool utilizes the Ark Vision model from the Volcano Engine to provide these capabilities. It is ideal for applications where visual data analysis is necessary, such as image classification, object detection, or text extraction from images.

Canonical page: https://skillsregistry.net/skills/kobexi26-mcp-vision  
JSON: https://api.skillsregistry.net/v1/skills/kobexi26-mcp-vision

## Description

通过火山引擎方舟视觉模型为无视觉能力的主模型提供识图能力的MCP服务器，支持图片描述和文字提取。

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bfhyyqnizm)
- **Repository:** <https://github.com/kobexi26/mcp-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": "kobexi26-mcp-vision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kobexi26-mcp-vision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kobexi26-mcp-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