Advertise
MCP.so
Sign In

Vision MCP Server | 图片分析 MCP

@Markusbetter

Repository

Basic information

Category

Media & Design

Last updated

Transports

stdio

Author

Markusbetter

Submitted by

Markus Lee

About 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 config

Add this server to your MCP-compatible client using the configuration below.

{
  "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 tools

1

分析图片内容并提供详细描述

Overview

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

Frequently asked questions

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.

Comments

More Media & Design MCP servers

Pexafy Stock Photos

Pexafy

Search millions of free-to-use photos from Unsplash, Pexels, Pixabay and more in one query. Describe the scene in any language, get real photos with licence and credit line. Hosted, no API key.

Layers Marketing MCP

layers

Give your agent marketing superpowers. Layers MCP is the endpoint your coding agent calls to run growth for your product: it finds what to post, renders the video or slideshow, delivers it to TikTok, reads the result, an

BulkTranscripts: YouTube Transcripts

Transcripts for one YouTube video or a whole channel or playlist, plus YouTube search, channel and playlist listings, and free new-upload tracking.

GPT Image 2.5 MCP

you.bot

Generate and edit images with GPT Image 2.5 for $0.029 each. A free you.bot key (not an OpenAI key) comes with 50 credits — about 17 images — and needs no credit card.

aicut

aicut

Make AI videos, images, voiceovers and full AI Video Story episodes from Claude, ChatGPT, Cursor or any MCP client, then post them to TikTok, YouTube and Instagram. Veo, Kling, Seedance and more, on your own aicut accoun

Advertise