FAL Image/Video MCP Server

Instructions

Implementation Reference

• src/index.ts:566-625 (handler)

  Core execution handler for the luma_ray2_image tool. Configures FAL client, calls the specific endpoint, processes video output with downloads/data URLs, and returns formatted result.

  private async handleImageToVideo(args: any, model: any) {
    const { 
      image_url, 
      prompt, 
      duration = '5', 
      aspect_ratio = '16:9',
      negative_prompt,
      cfg_scale
    } = args;
  
    try {
      // Configure FAL client lazily with query config override
      configureFalClient(this.currentQueryConfig);
      const inputParams: any = { image_url, prompt };
      
      // Add optional parameters
      if (duration) inputParams.duration = duration;
      if (aspect_ratio) inputParams.aspect_ratio = aspect_ratio;
      if (negative_prompt) inputParams.negative_prompt = negative_prompt;
      if (cfg_scale !== undefined) inputParams.cfg_scale = cfg_scale;
  
      const result = await fal.subscribe(model.endpoint, { input: inputParams });
      const videoData = result.data as FalVideoResult;
      const videoProcessed = await downloadAndProcessVideo(videoData.video.url, model.id);
  
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              model: model.name,
              id: model.id,
              endpoint: model.endpoint,
              input_image: image_url,
              prompt,
              video: {
                url: videoData.video.url,
                localPath: videoProcessed.localPath,
                ...(videoProcessed.dataUrl && { dataUrl: videoProcessed.dataUrl }),
                width: videoData.video.width,
                height: videoData.video.height,
              },
              metadata: inputParams,
              download_path: DOWNLOAD_PATH,
              data_url_settings: {
                enabled: ENABLE_DATA_URLS,
                max_size_mb: Math.round(MAX_DATA_URL_SIZE / 1024 / 1024),
              },
              autoopen_settings: {
                enabled: AUTOOPEN,
                note: AUTOOPEN ? "Files automatically opened with default application" : "Auto-open disabled"
              },
            }, null, 2),
          },
        ],
      };
    } catch (error) {
      throw new Error(`${model.name} generation failed: ${error}`);
    }
  }

• src/index.ts:380-390 (schema)

  Input schema definition for image-to-video tools including luma_ray2_image, specifying parameters like image_url, prompt, duration, etc.

  } else if (category === 'imageToVideo') {
    baseSchema.inputSchema.properties = {
      image_url: { type: 'string', description: 'URL of the input image' },
      prompt: { type: 'string', description: 'Motion description prompt' },
      duration: { type: 'string', enum: ['5', '10'], default: '5', description: 'Video duration in seconds' },
      aspect_ratio: { type: 'string', enum: ['16:9', '9:16', '1:1'], default: '16:9' },
      negative_prompt: { type: 'string', description: 'What to avoid in the video' },
      cfg_scale: { type: 'number', default: 0.5, minimum: 0, maximum: 1, description: 'How closely to follow the prompt' }
    };
    baseSchema.inputSchema.required = ['image_url', 'prompt'];
  }

• src/index.ts:119-127 (registration)

  MODEL_REGISTRY definition registering luma_ray2_image with its endpoint and metadata, used for tool discovery and dispatch.

  imageToVideo: [
    { id: 'ltx_video', endpoint: 'fal-ai/ltx-video-13b-distilled/image-to-video', name: 'LTX Video', description: 'Fast and high-quality image-to-video conversion' },
    { id: 'kling_master_image', endpoint: 'fal-ai/kling-video/v2.1/master/image-to-video', name: 'Kling 2.1 Master I2V', description: 'Premium image-to-video conversion' },
    { id: 'pixverse_image', endpoint: 'fal-ai/pixverse/v4.5/image-to-video', name: 'Pixverse V4.5 I2V', description: 'Advanced image-to-video' },
    { id: 'wan_pro_image', endpoint: 'fal-ai/wan-pro/image-to-video', name: 'Wan Pro I2V', description: 'Professional image animation' },
    { id: 'hunyuan_image', endpoint: 'fal-ai/hunyuan-video-image-to-video', name: 'Hunyuan I2V', description: 'Open-source image-to-video' },
    { id: 'vidu_image', endpoint: 'fal-ai/vidu/image-to-video', name: 'Vidu I2V', description: 'High-quality image animation' },
    { id: 'luma_ray2_image', endpoint: 'fal-ai/luma-dream-machine/ray-2/image-to-video', name: 'Luma Ray 2 I2V', description: 'Latest Luma image-to-video' }
  ]

• src/index.ts:404-408 (registration)

  Registration logic in list_tools handler that dynamically creates the tool schema for luma_ray2_image using generateToolSchema.

    tools.push(this.generateToolSchema(model, 'textToVideo'));
  }
  for (const model of MODEL_REGISTRY.imageToVideo) {
    tools.push(this.generateToolSchema(model, 'imageToVideo'));
  }

• src/index.ts:476-482 (handler)

  Dispatch logic in CallToolRequestSchema handler that identifies luma_ray2_image as imageToVideo category and calls the appropriate handler.

  if (MODEL_REGISTRY.imageGeneration.find(m => m.id === name)) {
    return await this.handleImageGeneration(args, model);
  } else if (MODEL_REGISTRY.textToVideo.find(m => m.id === name)) {
    return await this.handleTextToVideo(args, model);
  } else if (MODEL_REGISTRY.imageToVideo.find(m => m.id === name)) {
    return await this.handleImageToVideo(args, model);
  }