MCP Seedream

A Model Context Protocol (MCP) server for AI image generation and editing using ByteDance's Seedream models through the AceDataCloud API.

Generate and edit AI images directly from Claude, VS Code, or any MCP-compatible client.

Features

• Text-to-Image Generation — Create high-quality images from text prompts (Chinese & English)
• Image Editing — Modify existing images with AI (style transfer, background change, virtual try-on)
• Multiple Models — Seedream v4.5 (flagship), v4.0 (balanced), v3.0 T2I, SeedEdit v3.0 I2I
• Multi-Resolution — 1K, 2K, 4K, adaptive, and custom dimensions
• Seed Control — Reproducible results with seed parameter (v3 models)
• Sequential Generation — Generate related images in sequence (v4.5/v4.0)
• Streaming — Progressive image delivery (v4.5/v4.0)
• Task Tracking — Monitor generation progress and retrieve results

Quick Start

1. Get API Token

Get your API token from AceDataCloud Platform:

1. Sign up or log in
2. Navigate to Seedream Images API
3. Click "Acquire" to get your token

2. Install

# Install from PyPI
pip install mcp-seedream-pro

# Or clone and install locally
git clone https://github.com/AceDataCloud/MCPSeedream.git
cd MCPSeedream
pip install -e .

3. Configure

# Copy example environment file
cp .env.example .env

# Edit with your API token
echo "ACEDATACLOUD_API_TOKEN=your_token_here" > .env

4. Run

# Run the server
mcp-seedream-pro

# Or with Python directly
python main.py

Claude Desktop Integration

Add to your Claude Desktop configuration:

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

{
  "mcpServers": {
    "seedream": {
      "command": "mcp-seedream-pro",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Or if using uv:

{
  "mcpServers": {
    "seedream": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/MCPSeedream",
        "mcp-seedream-pro"
      ],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Remote HTTP Mode (Hosted)

AceDataCloud hosts a managed MCP server that you can connect to directly — no local installation required.

Endpoint: https://seedream.mcp.acedata.cloud/mcp

All requests require a Bearer token in the Authorization header. Get your token from AceDataCloud Platform.

Claude Desktop (Remote)

{
  "mcpServers": {
    "seedream": {
      "type": "streamable-http",
      "url": "https://seedream.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer your_api_token_here"
      }
    }
  }
}

Cursor / VS Code

In your MCP client settings, add:

• Type: streamable-http
• URL: https://seedream.mcp.acedata.cloud/mcp
• Headers: Authorization: Bearer your_api_token_here

cURL Test

# Health check (no auth required)
curl https://seedream.mcp.acedata.cloud/health

# MCP initialize (requires Bearer token)
curl -X POST https://seedream.mcp.acedata.cloud/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer your_api_token_here" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

Self-Hosting with Docker

docker pull ghcr.io/acedatacloud/mcp-seedream-pro:latest
docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-seedream-pro:latest

Clients connect with their own Bearer token — the server extracts the token from each request's Authorization header and uses it for upstream API calls.

Available Tools

Image Generation & Editing

Task Management

Information

Available Models

Usage Examples

Generate Image from Prompt

User: Create a photorealistic image of a cat in a garden

Claude: I'll generate that image for you.
[Calls seedream_generate_image with detailed prompt]
→ Returns task_id and image URL

Image Editing

User: Change the background of this photo to a beach
[Provides image URL]

Claude: I'll edit that image for you.
[Calls seedream_edit_image with image URL and edit description]

Chinese Prompt Support

User: 生成一幅中国山水画，有远山、流水和古松

Claude: 好的，我来为您生成这幅山水画。
[Calls seedream_generate_image with Chinese prompt]

Reproducible Generation

User: Generate a landscape and make sure I can recreate the exact same image later

Claude: I'll use the v3 model with a fixed seed.
[Calls seedream_generate_image with model=doubao-seedream-3-0-t2i-250415, seed=42]

Configuration

Environment Variables

Command Line Options

mcp-seedream-pro --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

# Clone repository
git clone https://github.com/AceDataCloud/MCPSeedream.git
cd MCPSeedream

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest -m integration

Code Quality

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools main.py

Build & Publish

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

MCPSeedream/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for Seedream API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   ├── server.py          # MCP server initialization
│   ├── types.py           # Type definitions
│   └── utils.py           # Utility functions
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── image_tools.py     # Image generation/editing tools
│   ├── task_tools.py      # Task query tools
│   └── info_tools.py      # Model & size info tools
├── prompts/                # MCP prompt templates
│   └── __init__.py
├── tests/                  # Test suite
│   ├── conftest.py
│   ├── test_config.py
│   └── test_utils.py
├── deploy/                 # Deployment configs
│   ├── run.sh
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .github/                # GitHub Actions workflows
│   ├── dependabot.yml
│   └── workflows/
│       ├── ci.yaml
│       ├── claude.yml
│       ├── deploy.yaml
│       └── publish.yml
├── .env.example           # Environment template
├── .gitignore
├── .ruff.toml             # Ruff linter config
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

API Reference

This server wraps the AceDataCloud Seedream API:

• Seedream Images API — Image generation and editing
• Seedream Tasks API — Task queries

Use Cases

• AI Art Creation — Generate stunning artwork, illustrations, and digital art
• Product Photography — Create professional product scene compositions
• Content Creation — Generate images for blogs, social media, marketing
• Virtual Try-On — Visualize clothing on different models
• Style Transfer — Transform photos into different art styles
• Game Design — Concept art, character design, environment design
• E-commerce — Product mockups, lifestyle shots, banner images

License

MIT License - see the LICENSE file for details.

Links

• AceDataCloud Platform
• Seedream API Documentation
• MCP Protocol
• GitHub Repository
• PyPI Package