MCP-VL

MCP 自动图片分析服务器

typescript

7

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lengbone-mcp-vl": {
      "command": "node",
      "args": [
        "/path/mcp-vl/dist/index.js"
      ],
      "env": {
        "ZHIPUAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run MCP-VL to automatically analyze images for code content and architecture using the GLM-4.5V model. It supports input from a file path or directly from the clipboard, making it easy to extract code text, analyze structure, detect issues, and generate documentation all in one streamlined workflow.

How to use

Use an MCP client to connect to MCP-VL and run the built-in tool that analyzes images. You can trigger analysis in two ways: point to an image file path or let the system grab the image from your clipboard. The tool can extract code text, identify the programming language, analyze architecture, detect potential issues, and generate documentation.

How to install

Prerequisites you need before installing MCP-VL:

Node.js 18+ is required to run the MCP server components.
A suitable package manager is installed (pnpm is used in common workflows).

Install dependencies and prepare the project with the following commands.

Additional configuration and run steps

Prepare environment variables and build the project as shown in the configuration steps.

Configuration and runtime example

You can run MCP-VL in local stdio mode. The command launches the MCP server script directly with Node. Ensure you provide your API key for the GLM-based image analysis service.

Available tools

auto_analyze_image

Auto-fetch and analyze an image from a file path or clipboard. Supports focus areas such as code, architecture, error, and documentation.