Jimeng Image

Provides an MCP interface to generate AI images using 即梦AI, with automatic polling and download to a configured folder.

python

0

GitHub Stars

python

Language

5 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": {
    "goodmannn-jimeng_mcp": {
      "command": "python",
      "args": [
        "/absolute/path/to/jimeng-mcp/server.py"
      ],
      "env": {
        "JIMENG_TOKEN": "your_session_id_here"
      }
    }
  }
}

You run an MCP server that exposes an image generation service powered by 即梦AI. This server handles drafting prompts, polling for completion, downloading results, and saving images in an ordered sequence for easy use with MCP clients like Claude Desktop or other copilots.

How to use

You connect an MCP client to the jimeng image generator server to request AI-generated images. Use the client to submit prompts, specify output folders, and receive ready-to-use image files. The server handles generating drafts, waiting for completion, downloading the results, and saving them in a predictable order (01.jpg, 02.jpg, etc.). You can operate the server either as a local process or through a client configuration that points to the server.

Usage patterns you can follow include initiating a generation request with a prompt and a target folder, then waiting for the server to return the saved image paths and URLs. The server supports configurable image dimensions and model parameters to suit different platforms and layouts.

How to install

Prerequisites: Python 3.8+ and internet access to install dependencies.

Install dependencies.

pip install -r requirements.txt

Set the authentication token in your environment.

export JIMENG_TOKEN="your_session_id_here"

Run the MCP server directly.

JIMENG_TOKEN="your_token" python server.py

Configuration and usage notes

Configure token management to keep your session secure and avoid embedding the token in code. The server reads JIMENG_TOKEN from the environment, or you can pass it when starting the server.

Start and use the server with an MCP client. The client can be configured to launch the server process and supply the token via environment variables.

Additional details and examples

MCP clients can submit a generation request with a prompt and a target folder. The server will poll for completion, download all generated images, and save them in the target folder with sequential names like 01.jpg, 02.jpg, etc.

Example usage from code (conceptual): you create a service, request an image, and then examine the saved files.

Available tools

generate_image

Generates AI images from a prompt, polls until completion, downloads all results, and saves them in a target folder with sequential filenames like 01.jpg, 02.jpg, etc.