Skip to main content
Glama
Jimeng MCP Server

Jimeng MCP Server

by ttkkasd

Jimeng MCP Server

A Model Context Protocol (MCP) server for Volcengine's Jimeng AI image generation service.

Features

  • Generate images using Volcengine's Jimeng AI service

  • Support for Chinese and English prompts

  • Configurable image dimensions and generation parameters

  • Watermark support

  • Built-in prompt enhancement (LLM preprocessing)

  • Super-resolution enhancement

Related MCP server: Jimeng MCP Server

Installation

npm install jimeng-mcp

Setup

  1. Get your Volcengine credentials from the Volcengine Console

  2. Set environment variables:

export VOLCENGINE_ACCESS_KEY_ID="your_access_key_id"
export VOLCENGINE_SECRET_ACCESS_KEY="your_secret_access_key"

Usage

With Claude Desktop

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "jimeng": {
      "command": "npx",
      "args": ["jimeng-mcp"],
      "env": {
        "VOLCENGINE_ACCESS_KEY_ID": "your_access_key_id",
        "VOLCENGINE_SECRET_ACCESS_KEY": "your_secret_access_key"
      }
    }
  }
}

Standalone Usage

# Set environment variables
export VOLCENGINE_ACCESS_KEY_ID="your_access_key_id"
export VOLCENGINE_SECRET_ACCESS_KEY="your_secret_access_key"

# Run the server
npm start

Available Tools

generateImage

Generate images using text descriptions.

Parameters:

  • prompt (required): Text description for image generation

  • req_key (optional): Model identifier (default: "jimeng_high_aes_general_v21_L")

  • seed (optional): Random seed for generation (default: -1)

  • width (optional): Image width in pixels (default: 512)

  • height (optional): Image height in pixels (default: 512)

  • use_sr (optional): Enable super-resolution (default: true)

  • use_pre_llm (optional): Enable prompt enhancement (default: true)

  • return_url (optional): Return image URLs (default: true)

  • logo_info (optional): Watermark configuration

Example:

{
  "prompt": "一只可爱的小猫在花园里玩耍,阳光明媚,高清摄影",
  "width": 1024,
  "height": 1024,
  "use_sr": true
}

Development

# Install dependencies
npm install

# Build
npm run build

# Development mode
npm run dev

# Lint
npm run lint

# Format
npm run format

Configuration

Environment Variables

  • VOLCENGINE_ACCESS_KEY_ID: Your Volcengine access key ID

  • VOLCENGINE_SECRET_ACCESS_KEY: Your Volcengine secret access key

Watermark Configuration

{
  "logo_info": {
    "add_logo": true,
    "position": 0,     // 0: bottom-right, 1: bottom-left, 2: top-left, 3: top-right
    "language": 0,     // 0: Chinese, 1: English
    "logo_text_content": "AI Generated",
    "opacity": 0.3
  }
}

API Reference

This MCP server interfaces with Volcengine's Jimeng image generation API. For detailed API documentation, visit:

License

MIT

Contributing

  1. Fork the repository

  2. Create your feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add some amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request

Support

For issues and questions:

Security

  • Never commit API keys or secrets to version control

  • Use environment variables for sensitive configuration

  • Regularly rotate your API credentials

Available Tools

1 tool
generateImageC

调用即梦AI生成图像

Inputs: prompt (required), req_key, seed, negative_prompt.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.9/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or confusion between tools. The single tool 'generateImage' has a clearly defined purpose that cannot be mistaken for any other tool in the set.

    Naming Consistency5/5

    The naming pattern cannot be inconsistent with only one tool. The tool name 'generateImage' follows a clear verb_noun pattern, and there are no other tools to create any inconsistency.

    Tool Count2/5

    A single tool is generally too few for most server purposes, as it offers limited functionality and may not cover the domain adequately. While it might suffice for a very narrow scope, it feels thin and underdeveloped for typical MCP server applications.

    Completeness2/5

    Based on the server name 'Jimeng MCP Server' and the tool description '调用即梦AI生成图像' (calls Jimeng AI to generate images), the domain appears to be image generation. However, with only one tool, there are significant gaps—no tools for modifying, retrieving, or managing generated images, making the surface severely incomplete for practical workflows.

    Related MCP Connectors

    Related MCP Servers