广告合作
MCP.so
登录

Vision MCP Server | 图片分析 MCP

@Markusbetter

代码仓库

基本信息

分类

媒体与设计

传输方式

stdio

作者

Markusbetter

提交者

Markus Lee

关于 Vision MCP Server | 图片分析 MCP

This MCP addresses the visual recognition limitations of text-based models by enabling accurate image description and identification, making it excellent for AI-assisted reference design interface analysis.

#vision#image-analysis#mcp

Vision MCP Server | 图片分析 MCP 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "vision-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "vision-mcp-server"
      ],
      "env": {
        "MODELSCOPE_TOKEN": "your_modelscope_token_here",
        "MODELSCOPE_MODEL": "Qwen/Qwen3-VL-30B-A3B-Instruct"
      }
    }
  }
}

Vision MCP Server | 图片分析 MCP 工具

1

分析图片内容并提供详细描述

概览

What is Vision Mcp Server | 图片分析 Mcp?

A Vision Analysis MCP server that provides image content analysis and description. It bridges text-only AI models with vision capabilities by using the free ModelScope vision model Qwen3-VL-30B-A3B-Instruct (configurable to other ModelScope vision models).

How to use Vision Mcp Server | 图片分析 Mcp?

Install via npx, global npm, or local npm. Configure in your MCP client with the environment variable MODELSCOPE_TOKEN (required) and optional MODELSCOPE_MODEL. Invoke the analyze_image tool with an image parameter (URL or local path) and an optional prompt.

Key features of Vision Mcp Server | 图片分析 Mcp

  • Supports local image files and online image URLs
  • Uses ModelScope’s free AI vision models
  • Fully compatible with the MCP protocol
  • TypeScript support with complete type definitions

Use cases of Vision Mcp Server | 图片分析 Mcp

  • Add vision analysis to a text‑only AI client
  • Describe the content of any image (local or URL)
  • Identify objects or answer questions about an image

常见问题

1

What model does it use by default?

It uses the free ModelScope model Qwen3‑VL‑30B‑A3B‑Instruct. You can change it via `MODELSCOPE_MODEL`.

2

What are the requirements?

A ModelScope API token (`MODELSCOPE_TOKEN`) is required. Node.js and npm are needed for installation.

3

Does it support local images?

Yes, both local file paths and online URLs are supported as input.

4

How is data handled?

Images are sent to the ModelScope API for analysis (based on the configured model).

5

What transport does it use?

It follows the MCP protocol; the README shows stdio configuration in client settings.

评论

媒体与设计 分类下的更多 MCP 服务器

LinkedIn Ads MCP

AdPlug

LinkedIn Ads MCP server by AdPlug, connecting LinkedIn Ads to Claude, ChatGPT and other MCP-compatible AI assistants. Analyse performance, audiences, creatives and conversions. Generate reports and manage campaigns, budg

Notch

Notch

Create finished video ads from chat. Give Notch a brief or product URL — it loads your brand context, writes the script, and produces the finished ad: avatar, scenes, voiceover, captions. Built for performance marketers,

Organize with AI (OwAI)

Alexander Visheratin

Search and manage photo and video libraries through AI assistants. Find images and video moments, review duplicates, and organize collections, groups, favorites and people across local folders, Apple Photos and OneDrive.

Generate Greetings

Generate Greetings

Create greetings and personalized PNG cards for 30 occasions in 15 languages, including Hindi, Greek and Hebrew. Free remote MCP with curated phrases, occasion-matched backgrounds and four styles, including motivational.

CoDesign

IMG.LY

Give your AI agent a real design engine. Create, edit and export real, editable designs from Claude Code, Codex, Cursor and more.

广告合作