home / mcp / doubao image description mcp server

Doubao Image Description MCP Server

Provides fast image descriptions using the Doubao model for MCP clients and connected apps.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "9527wow-doubao-image-mcp": {
      "url": "https://mcp.example.com/doubao-image",
      "headers": {
        "VOLCENGINE_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can run the Doubao Image Description MCP Server to enable image understanding for iFlow CLI and Claude Desktop. This server accepts images, processes them through the Doubao model, and returns descriptive text, enabling automated image descriptions and integrations with your workflows.

How to use

To use the Doubao Image Description MCP Server with an MCP client, first ensure the server is running, then connect your MCP client to it to request image descriptions for local or remote images.

How to install

Prerequisites: You need Python installed on your system. You may also use a dependency manager but Python is required to install the project requirements.

pip install -r requirements.txt

Configure the API key to access the image understanding service. You have two options: set an environment variable (recommended) or create a configuration file.

# Windows
set VOLCENGINE_API_KEY=YOUR_API_KEY

# Linux/Mac
export VOLCENGINE_API_KEY=YOUR_API_KEY

cp config.example.json config.json
```
Then edit config.json to include your API key and any other required settings.

Register the server with the iFlow MCP client to enable command routing to the local server. Use the path to your server script as shown.

iflow mcp add doubao-image-mcp python C:\\Users\\15579\\doubao-image-mcp\\server.py

Additional sections

Notes on usage include testing with a description command, providing either a local image path or a URL, and optionally a custom prompt in English to guide the description. You can describe a local image with a path, such as a local file path, or describe a network image via a URL.

The server supports multiple image formats and performs automatic optimization for large images to balance quality and speed. It is designed to deliver fast responses suitable for interactive applications.

Security and access: protect your API key and API access. Use environment variables where possible and limit access to trusted clients.

Examples of usage include describing a local image, describing a remote image, and describing with a custom prompt for English descriptions.