Docent (Image Description) MCP server

This MCP Docent Server is an AI-powered service that analyzes uploaded images and automatically generates descriptive text (docent explanations). The system leverages artificial intelligence to provide detailed descriptions for various types of images.

Installation

Prerequisites

• Node.js (v14 or higher)
• npm or yarn

Setup

1. Clone the repository:

git clone https://github.com/dong-project/mcp-docent-server.git
cd mcp-docent-server

2. Install dependencies:

npm install
# or with yarn
yarn install

3. Build the project:

npm run build
# or with yarn
yarn build

Usage

Starting the Server

To start the MCP Docent Server:

npm start
# or with yarn
yarn start

The server will start running on http://localhost:3000 by default.

Uploading Images for Analysis

You can upload images to the server via a POST request to the /analyze endpoint:

curl -X POST -F "image=@/path/to/your/image.jpg" http://localhost:3000/analyze

The server will respond with a JSON object containing the generated docent text:

{
  "description": "A detailed explanation of the image content generated by AI..."
}

Registering Custom Docent Tools

The server allows you to register additional docent tools for specialized image analysis:

import { registerDocentTool } from './tools/registerDocentTool';

// Register a custom docent tool
registerDocentTool({
  name: 'art-analyzer',
  description: 'Specialized in analyzing artwork',
  handler: async (imageBuffer) => {
    // Your custom logic for analyzing art images
    return 'This artwork appears to be...'
  }
});

Configuration Options

The server can be configured by setting environment variables:

# Set the server port
PORT=8080

# Configure AI model parameters
MODEL_TEMPERATURE=0.7
MODEL_MAX_TOKENS=500

# Start the server with custom configuration
npm start

Troubleshooting

Common Issues

• Image upload errors: Ensure your image file is in a supported format (JPG, PNG, WebP)
• Server connection issues: Check if the port is already in use by another application
• Slow response times: Large images may take longer to process; consider resizing before uploading

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "docent" '{"command":"npx","args":["-y","mcp-docent-server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "docent": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-docent-server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "docent": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-docent-server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect