# MCP Vision Server

> Use this tool when you need to analyze and extract information from images, enabling AI agents like Claude Code to describe visual content and recognize text within images. It solves problems such as image-based data extraction and accessibility, using local image files as input and generating descriptive text as output. Ideal for use cases where visual data needs to be converted into readable formats, such as text extraction or image description tasks.

Canonical page: https://skillsregistry.net/skills/coffe-d-mcp-vision-server  
JSON: https://api.skillsregistry.net/v1/skills/coffe-d-mcp-vision-server

## Description

Enables Claude Code to describe images and extract text using Kimi/Moonshot vision API. Supports local image files with customizable prompts.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rau879yqwj)
- **Repository:** <https://github.com/coffe-d/MCP-Vision-Server>

## 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": "coffe-d-mcp-vision-server"
    }
  }
}
```

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