Seedream

增强版 Seedream 4.0 MCP 工具 - 支持文生图、图生图、多图融合、组图生成，集成七牛云存储和提示词模板系统

python

GitHub Stars

python

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": {
    "joeseesun-seedream_mcp": {
      "command": "python",
      "args": [
        "/你的路径/Seedream_MCP/main.py"
      ],
      "env": {
        "LOG_FILE": "logs/seedream_mcp.log",
        "LOG_LEVEL": "INFO",
        "ARK_API_KEY": "YOUR_API_KEY",
        "ARK_BASE_URL": "https://ark.cn-beijing.volces.com/api/v3",
        "SEEDREAM_TIMEOUT": "60",
        "SEEDREAM_MODEL_ID": "doubao-seedream-4-0-250828",
        "SEEDREAM_API_TIMEOUT": "60",
        "SEEDREAM_MAX_RETRIES": "3",
        "SEEDREAM_DEFAULT_SIZE": "2K",
        "SEEDREAM_AUTO_SAVE_ENABLED": "true",
        "SEEDREAM_DEFAULT_WATERMARK": "false",
        "SEEDREAM_AUTO_SAVE_BASE_DIR": "./seedream_images",
        "SEEDREAM_AUTO_SAVE_DATE_FOLDER": "true"
      }
    }
  }
}

You have a Model Context Protocol (MCP) server built around Seedream 4.0 API to generate images from text, modify images, fuse multiple references, and create image sequences. This server lets you integrate image generation into your client tools with MCP-compatible commands, automatic local saving, and optional public hosting through cloud storage for easy sharing.

How to use

You connect to the Seedream MCP server from an MCP client by configuring a local or remote server entry. Use the provided stdio method to run the server locally, then point your MCP client to this local process. Once connected, you can issue requests to generate images from descriptions, edit images based on references, fuse multiple images into a new artwork, and generate sequential image stories. Each request can automatically save images locally and generate Markdown references for easy embedding.

How to install

Prerequisites: install Python 3.8+ on your system. You also need a Seedream 4.0 API key from Volcano Engine to access the Seedream services.

Step 1: Install the MCP package locally.

Step 2: Run the MCP server locally.

Additional configuration and usage notes

Configure your MCP client to talk to the Seedream MCP server via a local stdio connection. The standard setup is to run the server with Python and point the client to the server’s main script.

Usage examples and options

You can perform a text-to-image operation, an image-to-image edit, multi-image fusion, or a sequential image generation sequence. Each operation supports automatic local saving, optional public hosting URL, and a generated Markdown reference. Use a descriptive prompt and adjust size, watermark, and save options as needed.

Available tools

text_to_image

Generate an image from a text prompt with options for size and saving behavior.

image_to_image

Transform or edit an image using a prompt and a reference image.

multi_image_fusion

Fuse multiple reference images into a new artwork based on a prompt.

sequential_generation

Create a sequence of images that are thematically linked.

auto_save

Automatically download and store generated images locally with Markdown references.

Built by

VeilStrat

AI signals for GTM teams