# read-image-mcp

> Use this tool when you need to analyze images without native vision capabilities, enabling agents to describe, perform OCR, or extract structured data from images. It solves problems such as image description, text extraction, and data retrieval, providing a single interface for various vision tasks. The tool accepts image inputs and returns descriptive text or extracted data outputs via a stdio MCP server.

Canonical page: https://skillsregistry.net/skills/xiayangqun-read-image-mcp  
JSON: https://api.skillsregistry.net/v1/skills/xiayangqun-read-image-mcp

## Description

A stdio MCP server that enables agents without native vision to ask an OpenAI-compatible vision model to describe, OCR, or extract structured data from images via a single tool.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/i3gznouhq5)
- **Repository:** <https://github.com/xiayangqun/Read-Image-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": "xiayangqun-read-image-mcp"
    }
  }
}
```

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