{
  "markdown": "# SeedreamMCP\n\n<!-- mcp-name: io.github.AceDataCloud/mcp-seedream-pro -->\n\n[![PyPI version](https://img.shields.io/pypi/v/mcp-seedream-pro.svg)](https://pypi.org/project/mcp-seedream-pro/)\n[![PyPI downloads](https://img.shields.io/pypi/dm/mcp-seedream-pro.svg)](https://pypi.org/project/mcp-seedream-pro/)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![MCP](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://modelcontextprotocol.io)\n\nA [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for AI image generation and editing using [ByteDance's Seedream](https://www.volcengine.com/product/doubao) models through the [AceDataCloud API](https://platform.acedata.cloud).\n\nGenerate and edit AI images directly from Claude, VS Code, or any MCP-compatible client.\n\n## Features\n\n- **Text-to-Image Generation** — Create high-quality images from text prompts (Chinese & English)\n- **Image Editing** — Modify existing images, including transparent-background Pro edits\n- **Multiple Models** — Seedream v5.0 (flagship), v4.5, and v4.0\n- **Layer Decomposition** — Split one image into a base plus up to 16 editable transparent PNG layers\n- **Multi-Resolution** — Pro 1K/1.5K/2K; Lite 2K/3K/4K; custom dimensions\n- **Sequential Generation** — Generate related images in sequence (5.0 Lite/4.5/4.0)\n- **Web Search** — Let 5.0 Lite use current web information when needed\n- **Task Tracking** — Monitor generation progress and retrieve results\n\n## Tool Reference\n\n| Tool | Description |\n|------|-------------|\n| `seedream_generate_image` | Generate an AI image from a text prompt using ByteDance's Seedream model. |\n| `seedream_edit_image` | Edit images, including Seedream 5.0 Pro transparent-background mode. |\n| `seedream_decompose_image` | Split one image into a base and up to 16 positioned transparent layers. |\n| `seedream_get_task` | Query the status and result of a Seedream image generation or edit task. |\n| `seedream_get_tasks_batch` | Query multiple Seedream image tasks at once. |\n| `seedream_list_models` | List all available Seedream models with their capabilities and pricing. |\n| `seedream_list_sizes` | List all available image sizes and resolution options for Seedream. |\n\n## Seedream 5.0 capability matrix\n\n| Capability | 5.0 Pro | 5.0 Lite |\n|---|---:|---:|\n| Single image generation/editing | Yes | Yes |\n| Layer decomposition / transparent background | Yes | No |\n| Sequential images / web search | No | Yes |\n| Prompt optimization | standard, fast | standard |\n| Preset sizes | 1K, 1.5K, 2K | 2K, 3K, 4K |\n\nMCP image tools submit asynchronously and return a task id. Use `seedream_get_task` until completion. For real-time NDJSON streaming, call the REST API or CLI rather than combining `stream` with MCP async submission.\n\n## Quick Start\n\n### 1. Get Your API Token\n\n1. Sign up at [AceDataCloud Platform](https://platform.acedata.cloud)\n2. Go to the [API documentation page](https://platform.acedata.cloud/documents/seedream-images)\n3. Click **\"Acquire\"** to get your API token\n4. Copy the token for use below\n\n### 2. Use the Hosted Server (Recommended)\n\nAceDataCloud hosts a managed MCP server — **no local installation required**.\n\n**Endpoint:** `https://seedream.mcp.acedata.cloud/mcp`\n\nAll requests require a Bearer token. Use the API token from Step 1.\n\n#### Claude.ai\n\nConnect directly on [Claude.ai](https://claude.ai) with OAuth — **no API token needed**:\n\n1. Go to Claude.ai **Settings → Integrations → Add More**\n2. Enter the server URL: `https://seedream.mcp.acedata.cloud/mcp`\n3. Complete the OAuth login flow\n4. Start using the tools in your conversation\n\n#### Claude Desktop\n\nAdd to your config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n#### Cursor / Windsurf\n\nAdd to your MCP config (`.cursor/mcp.json` or `.windsurf/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n#### VS Code (Copilot)\n\nAdd to your VS Code MCP config (`.vscode/mcp.json`):\n\n```json\n{\n  \"servers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\nOr install the [Ace Data Cloud MCP extension](https://marketplace.visualstudio.com/items?itemName=acedatacloud.acedatacloud-mcp) for VS Code, which registers the hosted MCP servers with one-click setup.\n\n#### JetBrains IDEs\n\n1. Go to **Settings → Tools → AI Assistant → Model Context Protocol (MCP)**\n2. Click **Add** → **HTTP**\n3. Paste:\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n\n#### Claude Code\n\nClaude Code supports MCP servers natively:\n\n```bash\nclaude mcp add seedream --transport http https://seedream.mcp.acedata.cloud/mcp \\\n  -h \"Authorization: Bearer YOUR_API_TOKEN\"\n```\n\nOr add to your project's `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n#### Cline\n\nAdd to Cline's MCP settings (`.cline/mcp_settings.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n#### Amazon Q Developer\n\nAdd to your MCP configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n#### Roo Code\n\nAdd to Roo Code MCP settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n#### Continue.dev\n\nAdd to `.continue/config.yaml`:\n\n```yaml\nmcpServers:\n  - name: seedream\n    type: streamable-http\n    url: https://seedream.mcp.acedata.cloud/mcp\n    headers:\n      Authorization: \"Bearer YOUR_API_TOKEN\"\n```\n\n#### Zed\n\nAdd to Zed's settings (`~/.config/zed/settings.json`):\n\n```json\n{\n  \"language_models\": {\n    \"mcp_servers\": {\n      \"seedream\": {\n        \"url\": \"https://seedream.mcp.acedata.cloud/mcp\",\n        \"headers\": {\n          \"Authorization\": \"Bearer YOUR_API_TOKEN\"\n        }\n      }\n    }\n  }\n}\n```\n\n#### cURL Test\n\n```bash\n# Health check (no auth required)\ncurl https://seedream.mcp.acedata.cloud/health\n\n# MCP initialize\ncurl -X POST https://seedream.mcp.acedata.cloud/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Accept: application/json\" \\\n  -H \"Authorization: Bearer YOUR_API_TOKEN\" \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-03-26\",\"capabilities\":{},\"clientInfo\":{\"name\":\"test\",\"version\":\"1.0\"}}}'\n```\n\n### 3. Or Run Locally (Alternative)\n\nIf you prefer to run the server on your own machine:\n\n```bash\n# Install from PyPI\npip install mcp-seedream-pro\n# or\nuvx mcp-seedream-pro\n\n# Set your API token\nexport ACEDATACLOUD_API_TOKEN=\"your_token_here\"\n\n# Run (stdio mode for Claude Desktop / local clients)\nmcp-seedream-pro\n\n# Run (HTTP mode for remote access)\nmcp-seedream-pro --transport http --port 8000\n```\n\n#### Claude Desktop (Local)\n\n```json\n{\n  \"mcpServers\": {\n    \"seedream\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-seedream-pro\"],\n      \"env\": {\n        \"ACEDATACLOUD_API_TOKEN\": \"your_token_here\"\n      }\n    }\n  }\n}\n```\n\n#### Docker (Self-Hosting)\n\n```bash\ndocker pull ghcr.io/acedatacloud/mcp-seedream-pro:latest\ndocker run -p 8000:8000 ghcr.io/acedatacloud/mcp-seedream-pro:latest\n```\n\nClients connect with their own Bearer token — the server extracts the token from each request's `Authorization` header.\n\n## Available Tools\n\n### Image Generation & Editing\n\n| Tool                       | Description                                   |\n| -------------------------- | --------------------------------------------- |\n| `seedream_generate_image`  | Generate an image from a text prompt           |\n| `seedream_edit_image`      | Edit or modify existing images with AI         |\n\n### Task Management\n\n| Tool                       | Description                                   |\n| -------------------------- | --------------------------------------------- |\n| `seedream_get_task`        | Query a single task status and result          |\n| `seedream_get_tasks_batch` | Query multiple tasks at once                   |\n\n### Information\n\n| Tool                       | Description                                   |\n| -------------------------- | --------------------------------------------- |\n| `seedream_list_models`     | List available models with capabilities        |\n| `seedream_list_sizes`      | List available image size options               |\n\n## Available Models\n\n| Model | Version | Type | Best For | Price |\n|-------|---------|------|----------|-------|\n| `doubao-seedream-5-0-pro-260628` | v5.0 Pro | Generate/Edit | Single image, transparent background, layer decomposition | Tiered Credits |\n| `doubao-seedream-5-0-260128` | v5.0 Lite | Text-to-Image | Best quality, latest flagship, web search | See live pricing |\n| `doubao-seedream-4-5-251128` | v4.5 | Text-to-Image | Previous flagship, great quality | See live pricing |\n| `doubao-seedream-4-0-250828` | v4.0 | Text-to-Image | Best value, most tasks | See live pricing |\n\n## Usage Examples\n\n### Generate Image from Prompt\n\n```\nUser: Create a photorealistic image of a cat in a garden\n\nClaude: I'll generate that image for you.\n[Calls seedream_generate_image with detailed prompt]\n→ Returns task_id and image URL\n```\n\n### Image Editing\n\n```\nUser: Change the background of this photo to a beach\n[Provides image URL]\n\nClaude: I'll edit that image for you.\n[Calls seedream_edit_image with image URL and edit description]\n```\n\n### Chinese Prompt Support\n\n```\nUser: 生成一幅中国山水画，有远山、流水和古松\n\nClaude: 好的，我来为您生成这幅山水画。\n[Calls seedream_generate_image with Chinese prompt]\n```\n\n## Configuration\n\n### Environment Variables\n\n| Variable                    | Description                   | Default                     |\n| --------------------------- | ----------------------------- | --------------------------- |\n| `ACEDATACLOUD_API_TOKEN`    | API token from AceDataCloud   | **Required**                |\n| `ACEDATACLOUD_API_BASE_URL` | API base URL                  | `https://api.acedata.cloud` |\n| `ACEDATACLOUD_OAUTH_CLIENT_ID`  | OAuth client ID (hosted mode) | —                           |\n| `ACEDATACLOUD_PLATFORM_BASE_URL` | Platform base URL            | `https://platform.acedata.cloud` |\n| `SEEDREAM_REQUEST_TIMEOUT`  | Request timeout in seconds    | `1800`                      |\n| `LOG_LEVEL`                 | Logging level                 | `INFO`                      |\n\n### Command Line Options\n\n```bash\nmcp-seedream-pro --help\n\nOptions:\n  --version          Show version\n  --transport        Transport mode: stdio (default) or http\n  --port             Port for HTTP transport (default: 8000)\n```\n\n## Development\n\n### Setup Development Environment\n\n```bash\n# Clone repository\ngit clone https://github.com/AceDataCloud/SeedreamMCP.git\ncd SeedreamMCP\n\n# Create virtual environment\npython -m venv .venv\nsource .venv/bin/activate  # or `.venv\\Scripts\\activate` on Windows\n\n# Install with dev dependencies\npip install -e \".[dev,test]\"\n```\n\n### Run Tests\n\n```bash\n# Run unit tests\npytest\n\n# Run with coverage\npytest --cov=core --cov=tools\n\n# Run integration tests (requires API token)\npytest -m integration\n```\n\n### Code Quality\n\n```bash\n# Format code\nruff format .\n\n# Lint code\nruff check .\n\n# Type check\nmypy core tools main.py\n```\n\n### Build & Publish\n\n```bash\n# Install build dependencies\npip install -e \".[release]\"\n\n# Build package\npython -m build\n\n# Upload to PyPI\ntwine upload dist/*\n```\n\n## Project Structure\n\n```\nSeedreamMCP/\n├── core/                   # Core modules\n│   ├── __init__.py\n│   ├── client.py          # HTTP client for Seedream API\n│   ├── config.py          # Configuration management\n│   ├── exceptions.py      # Custom exceptions\n│   ├── server.py          # MCP server initialization\n│   ├── types.py           # Type definitions\n│   └── utils.py           # Utility functions\n├── tools/                  # MCP tool definitions\n│   ├── __init__.py\n│   ├── image_tools.py     # Image generation/editing tools\n│   ├── task_tools.py      # Task query tools\n│   └── info_tools.py      # Model & size info tools\n├── prompts/                # MCP prompt templates\n│   └── __init__.py\n├── tests/                  # Test suite\n│   ├── conftest.py\n│   ├── test_config.py\n│   └── test_utils.py\n├── deploy/                 # Deployment configs\n│   ├── run.sh\n│   └── production/\n│       ├── deployment.yaml\n│       ├── ingress.yaml\n│       └── service.yaml\n├── .github/                # GitHub Actions workflows\n│   ├── dependabot.yml\n│   └── workflows/\n│       ├── ci.yaml\n│       ├── claude.yml\n│       ├── deploy.yaml\n│       └── publish.yml\n├── .env.example           # Environment template\n├── .gitignore\n├── .ruff.toml             # Ruff linter config\n├── CHANGELOG.md\n├── Dockerfile             # Docker image for HTTP mode\n├── docker-compose.yaml    # Docker Compose config\n├── LICENSE\n├── main.py                # Entry point\n├── pyproject.toml         # Project configuration\n└── README.md\n```\n\n## API Reference\n\nThis server wraps the [AceDataCloud Seedream API](https://platform.acedata.cloud/documents/seedream-images):\n\n- [Seedream Images API](https://platform.acedata.cloud/documents/seedream-images) — Image generation and editing\n- [Seedream Tasks API](https://platform.acedata.cloud/documents/seedream-tasks) — Task queries\n\n## Use Cases\n\n- **AI Art Creation** — Generate stunning artwork, illustrations, and digital art\n- **Product Photography** — Create professional product scene compositions\n- **Content Creation** — Generate images for blogs, social media, marketing\n- **Virtual Try-On** — Visualize clothing on different models\n- **Style Transfer** — Transform photos into different art styles\n- **Game Design** — Concept art, character design, environment design\n- **E-commerce** — Product mockups, lifestyle shots, banner images\n\n## Documentation\n\n<!-- canonical-documentation -->\n[Documentation](https://platform.acedata.cloud/documents/seedream-mcp)\n\n## License\n\n[MIT License](LICENSE) - see the [LICENSE](LICENSE) file for details.\n\n## Links\n\n- [AceDataCloud Platform](https://platform.acedata.cloud)\n- [Seedream API Documentation](https://platform.acedata.cloud/documents/seedream-images)\n- [MCP Protocol](https://modelcontextprotocol.io)\n- [GitHub Repository](https://github.com/AceDataCloud/SeedreamMCP)\n- [PyPI Package](https://pypi.org/project/mcp-seedream-pro/)\n",
  "bytes": 15495,
  "sha": "c406180c8ba5d619a7d740fb1756fd5e98d345b07d96fee8b8d27defa0d4f2e2",
  "repo_slug": "acedatacloud/seedreammcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_acedatacloud_mcp_seedream_pro_7524db14/readme"
}