SeedreamMCP

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, including transparent-background Pro edits

• Multiple Models — Seedream v5.0 (flagship), v4.5, and v4.0

• Layer Decomposition — Split one image into a base plus up to 16 editable transparent PNG layers

• Multi-Resolution — Pro 1K/1.5K/2K; Lite 2K/3K/4K; custom dimensions

• Sequential Generation — Generate related images in sequence (5.0 Lite/4.5/4.0)

• Web Search — Let 5.0 Lite use current web information when needed

• Task Tracking — Monitor generation progress and retrieve results

Related MCP server: Doubao Image/Video Generation MCP Server

Tool Reference

Seedream 5.0 capability matrix

MCP 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.

Verify the connection before generating

After installation, discover the server's tools and call seedream_list_models with no arguments. This reference tool returns locally defined model or action information without calling a generation API. It does not validate your application key, account balance, service access, or current price. Your client's Chat model can still create separate charges.

To check authenticated access without creating media, query a task already owned by your application using the task-lookup tool and the same original task ID. If you have no existing task, stop after discovery/reference output; do not generate media just to test installation. Review current pricing before any new generation.

For missing tools, reconnect and refresh the tool list. For 401/403, check the existing application's key, service permissions, Allowed APIs, expiration and usage limit before replacing credentials. Keep a task/trace ID for other failures, never your key; do not automatically retry a paid operation.

Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is https://seedream.mcp.acedata.cloud/mcp. Choose one route for the MCP client:

The hosted service advertises OAuth metadata and Dynamic Client Registration (DCR). DCR registers the client application; it is not an API key. OAuth signs you in and the client sends the resulting Bearer token; it may reuse or create an API credential for the account. Browser sign-in still requires an AceDataCloud account. The hosted service can be metered: review current service documentation and displayed pricing before a real operation. Do not configure both an OAuth login and a fixed Authorization header for the same server.

Hosted OAuth examples

• Claude and Claude Desktop chat: Add a remote custom connector in Customize → Connectors → Add custom connector, enter https://seedream.mcp.acedata.cloud/mcp, select sign-in, and choose Register automatically if Claude asks how to register its OAuth client. Complete consent. Claude Desktop's local claude_desktop_config.json is a separate setup. Claude connector guide.

• Claude Code: claude mcp add --transport http --scope user seedream https://seedream.mcp.acedata.cloud/mcp, then start claude, open /mcp, and authenticate the Seedream server. Claude Code MCP guide.

• Cursor: Add a remote server with only https://seedream.mcp.acedata.cloud/mcp. For a project, merge the entry below into <project>/.cursor/mcp.json; for personal use, use ~/.cursor/mcp.json. Cursor MCP guide.

• VS Code / Copilot: Run MCP: Add Server, select HTTP, enter https://seedream.mcp.acedata.cloud/mcp, then finish the browser sign-in. New portable workspace configs use <project>/.mcp.json; the VS Code-specific format below uses <project>/.vscode/mcp.json or the user profile. Check MCP: List Servers. VS Code MCP setup.

• Codex: codex mcp add seedream --url https://seedream.mcp.acedata.cloud/mcp, then codex mcp login seedream. Its user settings are in ~/.codex/config.toml. Official Codex MCP guide.

Cursor project config (OAuth):

{
  "mcpServers": {
    "seedream": {"url": "https://seedream.mcp.acedata.cloud/mcp"}
  }
}

VS Code-specific workspace config (OAuth):

{
  "servers": {
    "seedream": {"type": "http", "url": "https://seedream.mcp.acedata.cloud/mcp"}
  }
}

Hosted API token

1. Open Ace Data Cloud → Applications. Sign in, or register an account first.

2. Find General application. If it has not been created, choose Initialize General Application. A general key can use the services available to your account; a dedicated application's key is limited to its service. Check the required service/model access and current pricing.

3. Copy the API Key from the application card, or open Keys / Manage Keys → Create to create a separate key for this integration. Give it a recognizable name so you can revoke or rotate it independently.

4. When creating a key, review Expiration Time, Set Usage Limitation, and Allowed APIs. Enable only the restrictions you need, allow the operations you will call, then click Create and copy the token from the key list. Task lookup does not grant permission to submit a generation. Confirm the application's balance can cover your first request; any trial allowance is whatever your account currently displays.

5. Copy only the token value, without quotation marks, spaces, or Bearer . An API Key / API Token field expects this raw value; only a manually configured HTTP Authorization header needs the Bearer prefix. A platform-... account-management token cannot replace a generation API key.

Save the key in the client's credential store or the environment variable shown below. Never put it in a prompt, shared workflow, screenshot, or Git commit. If authentication fails, check the full copied value, application/service access, expiration, usage limit, and balance before creating another key.

A fixed Bearer header bypasses OAuth. If the header is invalid, remove it before trying browser sign-in; keep the saved credential private.

For Claude Code, the shell expands the token when you add the server; treat the saved user MCP config as a secret:

export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
claude mcp add --transport http --scope user seedream https://seedream.mcp.acedata.cloud/mcp \
  --header "Authorization: Bearer $ACEDATACLOUD_API_TOKEN"

For a Claude Code project config, put a variable reference in <project>/.mcp.json and set that variable in the environment that launches Claude Code:

{
  "mcpServers": {
    "seedream": {
      "type": "http",
      "url": "https://seedream.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"}
    }
  }
}

Cursor uses a different environment-variable syntax in ~/.cursor/mcp.json or an uncommitted project config:

{
  "mcpServers": {
    "seedream": {
      "url": "https://seedream.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${env:ACEDATACLOUD_API_TOKEN}"}
    }
  }
}

In VS Code, run MCP: Open User Configuration and merge this server plus its masked input; ${input:...} is for VS Code's user/workspace format and is not portable to the Agent Host .mcp.json format:

{
  "inputs": [
    {"id": "acedata-seedream-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}
  ],
  "servers": {
    "seedream": {
      "type": "http",
      "url": "https://seedream.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${input:acedata-seedream-token}"}
    }
  }
}

For Cline, use its MCP configuration UI or CLI file ~/.cline/data/settings/cline_mcp_settings.json; its remote transport value is streamableHttp. For JetBrains AI Assistant, add a remote URL from Settings → Tools → AI Assistant → Model Context Protocol (MCP). For Zed, use a context_servers entry with the URL only for OAuth or add a local Bearer header. These clients have different configuration schemas; follow their current UI rather than copying another client's JSON. Cline · JetBrains · Zed.

Local stdio

Install the package and give the local process an API token:

python -m pip install mcp-seedream-pro
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
mcp-seedream-pro

For Claude Desktop local MCP, merge this entry into the file opened by its developer settings (~/Library/Application Support/Claude/claude_desktop_config.json on macOS). uvx requires uv on PATH:

{
  "mcpServers": {
    "seedream": {
      "command": "uvx",
      "args": ["mcp-seedream-pro"],
      "env": {"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"}
    }
  }
}

Keep this user-level file private. Self-hosted HTTP uses mcp-seedream-pro --transport http --port 8000; expose it only with suitable network and TLS controls. Local execution still calls the AceDataCloud API.

Check before using the service

1. https://seedream.mcp.acedata.cloud/health returning {"status":"ok"} checks endpoint reachability only.

2. Confirm that the MCP client loads tools. seedream_list_models is a local reference tool with no generation API charge; it does not verify downstream API access or balance. Generation, editing, and decomposition create credit-consuming tasks and are marked as non-read-only operations. These annotations describe the operation; the client's version, permission settings, and organization policy determine whether it asks for approval. Review the input and current price before allowing a paid operation.

3. If you need a full API check, call seedream_generate_image with your own valid input after reviewing current service documentation and displayed pricing. If the result contains a task ID, call seedream_get_task on that same ID until terminal success or failure. Do not resubmit the operation just to check progress.

For 401, check which auth route the client used and whether the token or OAuth session is valid. A 403 may mean an account permission or content moderation failure; read the returned error. Insufficient balance and downstream service failures need their own diagnosis. A listed tool or submitted task does not prove a successful result.

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]

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/SeedreamMCP.git
cd SeedreamMCP

# 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

SeedreamMCP/
├── 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

Documentation

Documentation

License

MIT License - see the LICENSE file for details.

Links

• AceDataCloud Platform

• Seedream API Documentation

• MCP Protocol

• GitHub Repository

• PyPI Package