Generate images using Bytedance's SeedDream 3.0 model via the Replicate platform.
A Model Context Protocol (MCP) server that provides image generation capabilities using Bytedance's SeedDream 3.0 model via the Replicate platform.
SeedDream 3.0 is a bilingual (Chinese and English) text-to-image model that excels at:
generate_image
Generate a single image from a text prompt using SeedDream 3.0 via Replicate.
Parameters:
prompt
(required): Text description of the image to generate (supports English and Chinese)aspect_ratio
(optional): Image aspect ratio - one of: 1:1
, 3:4
, 4:3
, 16:9
, 9:16
, 2:3
, 3:2
, 21:9
, custom
(default: 16:9
)size
(optional): Image size - one of: small
, regular
, big
(default: regular
)
small
: Shortest dimension 512pxregular
: Always 1 megapixelbig
: Longest dimension 2048pxcustom
width
(optional): Image width in pixels (512-2048, only used when aspect_ratio is custom
)height
(optional): Image height in pixels (512-2048, only used when aspect_ratio is custom
)guidance_scale
(optional): Prompt adherence, higher = more literal (1.0-10.0, default: 2.5)seed
(optional): Random seed for reproducible results (0-2147483647)Replicate API Token: Get your API token from Replicate
Node.js: Ensure you have Node.js installed (version 16 or higher)
The easiest way to use this server is through npx, which automatically downloads and runs the latest version:
Add the server to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"seedream": {
"command": "npx",
"args": [
"-y",
"https://github.com/PierrunoYT/seedream-v3-replicate-mcp-server.git"
],
"env": {
"REPLICATE_API_TOKEN": "r8_your_replicate_token_here"
}
}
}
}
Add to your MCP settings file at:
C:\Users\[username]\AppData\Roaming\Code\User\globalStorage\kilocode.kilo-code\settings\mcp_settings.json
{
"mcpServers": {
"seedream": {
"command": "npx",
"args": [
"-y",
"https://github.com/PierrunoYT/seedream-v3-replicate-mcp-server.git"
],
"env": {
"REPLICATE_API_TOKEN": "r8_your_replicate_token_here"
},
"disabled": false,
"alwaysAllow": []
}
}
}
✅ Universal Access: Works on any machine with Node.js ✅ No Local Installation: npx downloads and runs automatically ✅ Always Latest Version: Pulls from GitHub repository ✅ Cross-Platform: Windows, macOS, Linux compatible ✅ Settings Sync: Works everywhere you use your MCP client
If you prefer to install locally:
Clone the repository
git clone https://github.com/PierrunoYT/seedream-v3-replicate-mcp-server.git
cd seedream-v3-replicate-mcp-server
Install dependencies
npm install
Build the server
npm run build
Use absolute path in configuration
{
"mcpServers": {
"seedream": {
"command": "node",
"args": ["/absolute/path/to/seedream-v3-replicate-mcp-server/build/index.js"],
"env": {
"REPLICATE_API_TOKEN": "r8_your_replicate_token_here"
}
}
}
}
Helper script to get the absolute path:
npm run get-path
Once configured, you can use the server through your MCP client:
Generate an image of a serene mountain landscape at sunset with a lake reflection
Create a portrait-oriented image of a futuristic cityscape (aspect ratio 9:16)
Generate 3 variations of a cute robot character
Generate images for these prompts: "a red rose", "a blue ocean", "a green forest"
生成一张中国传统山水画的图片
Generate a photorealistic portrait of a person reading a book in a library (guidance scale: 7.5)
The server returns detailed information about generated images:
Successfully generated 1 image(s) using SeedDream 3.0:
Prompt: "a serene mountain landscape at sunset"
Aspect Ratio: 1:1
Guidance Scale: 2.5
Seed Used: 1234567890
Generated Images:
Image 1 (1024x1024): https://v3.fal.media/files/...
# Test the server directly
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | node build/index.js
npm run watch
npm run inspector
"REPLICATE_API_TOKEN environment variable is not set"
"Server not showing up in Claude"
"Generation failed"
"npx command not found"
node --version
and npm --version
to verify installation✅ Robust Error Handling: Server continues running even without API token
✅ Graceful Shutdown: Proper handling of SIGINT and SIGTERM signals
✅ User-Friendly Messages: Clear error messages with setup instructions
✅ No More Crashes: Eliminated process.exit()
calls that caused connection drops
The server outputs debug information to stderr, which can help diagnose issues:
Image generation costs are determined by Replicate's pricing structure. Check Replicate Pricing for current rates.
This project is licensed under the MIT License - see the LICENSE file for details.
For issues related to:
process.exit()
calls that caused server crashesAn MCP server for Reptor/SysReptor that exposes the reptor CLI tool as a programmable service, configured via environment variables.
Analyze Solana metrics from InfluxDB and generate Grafana dashboards.
Enables AI assistants to use a Neo4j knowledge graph for standardized coding workflows, acting as a dynamic instruction manual and project memory.
Official MCP server for Buildable AI-powered development platform. Enables AI assistants to manage tasks, track progress, get project context, and collaborate with humans on software projects.
Fetch comprehensive information about CRAN packages, including READMEs, metadata, and search functionality.
Installs other MCP servers from their source repositories, requiring npx for Node.js and uv for Python.
Access WordPress development rules and best practices from the WordPress LLM Rules repository. It dynamically creates tools for each rule and caches content using Cloudflare Durable Objects.
An example of deploying a remote MCP server on Cloudflare Workers without authentication.
A local MCP server for developers that mirrors your in-development MCP server, allowing seamless restarts and tool updates so you can build, test, and iterate on your MCP server within the same AI session without interruption.
Performs data enrichment on observables using third-party services via the security-cli Python package.