{"id":"af529ce9-6032-4885-bdf2-d4629939583e","slug":"smithery-madhusudan-kulkarni-mcp-fal-ai-image","name":"fal.ai Image Generation Server","description":"MCP fal.ai Image Server\n\nEffortlessly generate images from text prompts using fal.ai and the Model Context Protocol (MCP). Integrates directly with AI IDEs like Cursor and Windsurf.\n\n## When and Why to Use\n\nThis tool is designed for:\n- Developers and designers who want to generate images from text prompts without leaving their IDE.\n- Rapid prototyping of UI concepts, marketing assets, or creative ideas.\n- Content creators needing unique visuals for blogs, presentations, or social media.\n- AI researchers and tinkerers experimenting with the latest fal.ai models.\n- Automating workflows that require programmatic image generation via MCP.\n\nKey features:\n- Supports any valid fal.ai model and all major image parameters.\n- Works out of the box with Node.js and a fal.ai API key.\n- Saves images locally with accessible file paths.\n- Simple configuration and robust error handling.\n\n## Quick Start\n\n1. Requirements: Node.js 18+, fal.ai API key\n2. Configure MCP:\n   {\n     \"mcpServers\": {\n       \"fal-ai-image\": {\n         \"command\": \"npx\",\n         \"args\": [\"-y\", \"mcp-fal-ai-image\"],\n         \"env\": { \"FAL_KEY\": \"YOUR-FAL-AI-API-KEY\" }\n       }\n     }\n   }\n3. Run: Use the generate-image tool from your IDE.\n\n💡 Typical Workflow:\nDescribe the image you want (e.g., “generate a landscape with flying cars using model fal-ai/kolors, 2 images, landscape_16_9”) and get instant results in your IDE.\n\n### 🗨️ Example Prompts\n\n- generate an image of a red apple\n- generate an image of a red apple using model fal-ai/kolors\n- generate 3 images of a glowing red apple in a futuristic city using model fal-ai/recraft-v3, square_hd, 40 inference steps, guidance scale 4.0, safety checker on\n\nSupported parameters: prompt, model ID (any fal.ai model), number of images, image size, inference steps, guidance scale, safety checker.\n\nImages are saved locally; file paths are shown in the response. For model IDs, see fal.ai/models.\n\n## Troubleshooting\n\n- FAL_KEY environment variable is not set: Set your fal.ai API key as above.\n- npx not found: Install Node.js 18+ and npm.\n\nAdvanced: Example MCP Request/Response\n\nRequest:\n{\n  \"tool\": \"generate-image\",\n  \"args\": {\n    \"prompt\": \"A futuristic cityscape at sunset\",\n    \"model\": \"fal-ai/kolors\"\n  }\n}\n\nExample response:\n{\n  \"images\": [\n    { \"url\": \"file:///path/to/generated_image1.png\" },\n    { \"url\": \"file:///path/to/generated_image2.png\" }\n  ]\n}\n\n## 📁 Image Output Directory\n\nGenerated images are saved to your local system:\n\n- By default: ~/Downloads/fal_ai (on Linux/macOS; uses XDG standard if available)\n- Custom location: Set the environment variable FAL_IMAGES_OUTPUT_DIR to your desired folder. Images will be saved in /fal_ai.\n\nThe full file path for each image is included in the tool's response.\n\n## ⚠️ Error Handling & Troubleshooting\n\n- If you specify a model ID that is not supported by fal.ai, you will receive an error from the backend. Double-check for typos or visit fal.ai/models to confirm the model ID.\n- For the latest list of models and their capabilities, refer to the fal.ai model catalog or API docs.\n- For other errors, consult your MCP client logs or open an issue on GitHub.\n\n## 🤝 Contributing\n\nContributions and suggestions are welcome! Please open issues or pull requests on GitHub.\n\n## 🔒 Security\n\n- Your API key is only used locally to authenticate with fal.ai.\n- No user data is stored or transmitted except as required by fal.ai API.\n\n## 🛡 License\n\nMIT License © 2025 Madhusudan Kulkarni","capabilities":[],"protocols":["MCP"],"safetyScore":86,"overallRank":22.9,"trustScore":null,"trust":null,"source":"SMITHERY","updatedAt":"2026-04-15T00:48:51.823Z"}