seedream-v4-fal
A Model Context Protocol (MCP) server that provides image generation capabilities using Bytedance's SeedDream 4.0 model via the FAL AI platform.
claude mcp add --transport stdio pierrunoyt-seedream-v4-fal-mcp-server npx -y https://github.com/PierrunoYT/seedream-v4-fal-mcp-server.git \ --env FAL_KEY="your-fal-api-key-here"
How to use
SeedDream 4.0 FAL MCP Server provides image generation capabilities by interfacing with Bytedance's SeedDream 4.0 model via the FAL AI platform. The server exposes tools to generate single images or batches of images from text prompts, with configurable image sizes and safety checks. The primary tools are generate_image for individual or multiple prompts and generate_image_batch for batching several prompts in one request. After configuring the MCP client, you can request images by supplying prompts, desired image sizes (preset or custom), and optional parameters like seed, number of images, and safety checker settings. The server returns detailed information about generated images, including the final image paths and metadata such as size, prompt, and seed.
To use, add seedream4 to your MCP client configuration (e.g., Claude Desktop or Kilo Code settings) and provide your FAL API key. Then craft prompts and optional parameters (image_size, num_images, seed, sync_mode, enable_safety_checker) to generate outputs. For batch requests, supply an array of prompts to generate_image_batch and specify a common size and safety preference. If you need higher quality or specific dimensions, choose from the supported presets or provide a custom width/height within the 1024–4096 range and observe the safety checker settings as needed.
How to install
Prerequisites:\n- Node.js (version 16 or higher)\n- FAL AI API Key (from fal.ai)\n\nQuick Setup (recommended)\nThe server can be run via npx without local installation. This pulls the latest version directly from GitHub and runs it with your FAL key.\n\n1) Ensure Node.js is installed and your environment has access to npm/npx.\n2) Use npx to run the server with your API key:\nbash\n# Replace with your actual FAL key\nnpx -y https://github.com/PierrunoYT/seedream-v4-fal-mcp-server.git\n\n3) When using MCP clients, set the FAL_KEY environment variable in your client configuration as shown in the example below.\n\nManual Installation (Alternative)\n1. Clone the repository and install dependencies:\nbash\ngit clone https://github.com/PierrunoYT/seedream-v4-fal-mcp-server.git\ncd seedream-v4-fal-mcp-server\nnpm install\n\n2. Build the server (if applicable):\nbash\nnpm run build\n\n3. Run locally or point your MCP configuration to the built index.js. Example configuration snippet:\njson\n{\n "mcpServers": {\n "seedream4": {\n "command": "node",\n "args": ["/absolute/path/to/seedream-v4-fal-mcp-server/build/index.js"],\n "env": {\n "FAL_KEY": "your-fal-api-key-here"\n }\n }\n }\n}\n\n4. If you need the absolute path, you can use a helper script like npm run get-path as documented in the repository.\n
Additional notes
Tips and troubleshooting: Ensure your FAL_KEY is valid and has sufficient credits; the server will log a helpful message if the key is missing. For npx usage, Node.js must be installed on the client machine. When using manual installation, verify that the absolute path to build/index.js is correct. Image sizes must be within 1024–4096 and follow the preset formats described in the docs. If the server does not appear in Claude or your MCP client, confirm that the JSON configuration is valid and that the environment variable is correctly set in the client configuration. The Safe Check (enable_safety_checker) helps filter inappropriate content, and you can toggle it per request if the API and model configuration permit.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.