@felores/kie-ai-mcp-server 3.2.0 → 3.2.1

package/README.md

@@ -6,7 +6,7 @@ Kie.ai offers **30-50% lower cost** than competitors with 99.9% uptime and 24/7
 
 ## 📚 Documentation
 
-- **[Complete Tool Reference](docs/TOOLS.md)** - Detailed documentation for all 21 AI tools
+- **[Complete Tool Reference](docs/TOOLS.md)** - Detailed documentation for all 24 AI tools
 - **[Database & Task Management](docs/DATABASE.md)** - SQLite database and task lifecycle  
 - **[Administrator Configuration](docs/ADMIN.md)** - Deployment guides and environment setup
 - **[Intelligent Features](docs/INTELLIGENCE.md)** - Smart mode detection and cost optimization
@@ -33,10 +33,9 @@ The easiest way to use this server is to add it to your MCP client configuration
 
 **That's it!** No callback URL setup required - the server handles it automatically.
 
-<details>
-<summary><strong>🎛️ Filter Tools (optional - click to expand)</strong></summary>
+### 🎛️ Enable Only the Tools You Need
 
-Reduce cognitive load by enabling only the tools you need:
+25 tools is a lot. Reduce cognitive load by enabling only what you use. Add the env var to the config above:
 
 **Whitelist (enable specific tools only):**
 ```json
@@ -47,48 +46,26 @@ Reduce cognitive load by enabling only the tools you need:
       "args": ["-y", "@felores/kie-ai-mcp-server"],
       "env": {
         "KIE_AI_API_KEY": "your-api-key-here",
-        "KIE_AI_ENABLED_TOOLS": "nano_banana_image,veo3_generate_video,suno_generate_music"
+        "KIE_AI_ENABLED_TOOLS": "gpt_image_2,wan_video,suno_generate_music"
       }
     }
   }
 }
 ```
 
-**Category filter (enable by type):**
+**Category filter (enable all image + video tools):**
 ```json
-{
-  "mcpServers": {
-    "kie-ai": {
-      "command": "npx",
-      "args": ["-y", "@felores/kie-ai-mcp-server"],
-      "env": {
-        "KIE_AI_API_KEY": "your-api-key-here",
-        "KIE_AI_TOOL_CATEGORIES": "image,video"
-      }
-    }
-  }
-}
+"KIE_AI_TOOL_CATEGORIES": "image,video"
 ```
 
 **Blacklist (disable specific tools):**
 ```json
-{
-  "mcpServers": {
-    "kie-ai": {
-      "command": "npx",
-      "args": ["-y", "@felores/kie-ai-mcp-server"],
-      "env": {
-        "KIE_AI_API_KEY": "your-api-key-here",
-        "KIE_AI_DISABLED_TOOLS": "midjourney_generate,runway_aleph_video"
-      }
-    }
-  }
-}
+"KIE_AI_DISABLED_TOOLS": "midjourney_generate,runway_aleph_video"
 ```
 
-**Categories:** `image` | `video` | `audio` — Utility tools (list_tasks, get_task_status) are always enabled.
+**Categories:** `image` (9) | `video` (11) | `audio` (3) -- Utility tools (`list_tasks`, `get_task_status`) are always enabled.
 
-</details>
+**Priority:** `ENABLED_TOOLS` > `TOOL_CATEGORIES` > `DISABLED_TOOLS` > all tools (default)
 
 **For Claude Desktop:** Add this to `~/Library/Application Support/Claude/claude_desktop_config.json` (Mac) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows)
 
@@ -106,7 +83,6 @@ Reduce cognitive load by enabling only the tools you need:
 ### 🚀 All AI Models in One API
 
 - **Google Veo 3**: Cinematic video generation with synchronized audio and 1080p output
-- **OpenAI Sora 2**: Advanced video generation with text/image/storyboard modes (unified)
 - **Runway Aleph**: Advanced video editing with object removal and style transfer
 - **Suno V5**: Professional music generation with realistic vocals up to 8 minutes
 - **Nano Banana 2**: Lightning-fast image generation and editing with Google Search grounding (unified tool)
@@ -114,9 +90,10 @@ Reduce cognitive load by enabling only the tools you need:
 - **ByteDance Seedance**: High-quality video with text-to-video and image-to-video (unified)
 - **ByteDance Seedream V5 Lite**: Advanced image generation and editing with unified interface
 - **Qwen**: Powerful image generation and editing with acceleration options (unified)
-- **OpenAI 4o Image**: Advanced image generation, editing, and variant creation with GPT-4o (unified)
+- **GPT Image 2**: Advanced image generation and editing with up to 16 reference images (unified)
 - **Flux Kontext**: Professional image generation and editing with advanced features (unified)
-- **Alibaba Wan 2.5**: High-quality video generation with text-to-video and image-to-video (unified)
+- **Alibaba Wan 2.7**: Multi-mode video generation with T2V, I2V, R2V, and video-edit (unified)
+- **HappyHorse 1.0**: Multi-mode video generation with T2V, I2V, R2V (9 refs), and video-edit with audio
 - **Hailuo 02**: Professional video generation with text-to-video and image-to-video modes (unified, standard/pro quality)
 - **Kling 3.0**: Advanced video generation with 3-15s duration, multi-shot storytelling, and native audio
 - **Midjourney AI**: Industry-leading image and video generation with multiple modes (unified)
@@ -164,16 +141,16 @@ Your AI assistant can research and learn about available models before using the
 - `kie://guides/video-models-comparison` - Feature matrix for all video models
 - `kie://guides/quality-optimization` - Cost/quality strategies
 
-### 🛠️ 21 Unified AI Tools
+### 🛠️ 24 Unified AI Tools
 
 All tools feature **smart mode detection** - one tool does multiple things:
 
 | Category | Tools |
 |----------|-------|
-| **Image (7)** | `bytedance_seedream_image`, `qwen_image`, `nano_banana_image`, `flux_kontext_image`, `openai_4o_image`, `recraft_remove_background`, `ideogram_reframe` |
-| **Video (8)** | `veo3_generate_video`, `sora_video`, `bytedance_seedance_video`, `wan_video`, `hailuo_video`, `kling_video`, `runway_aleph_video`, `midjourney_generate` |
+| **Image (9)** | `nano_banana_image`, `bytedance_seedream_image`, `qwen_image`, `gpt_image_2`, `flux_kontext_image`, `flux2_image`, `topaz_upscale_image`, `recraft_remove_background`, `ideogram_reframe` |
+| **Video (10)** | `veo3_generate_video`, `bytedance_seedance_video`, `wan_video`, `happyhorse_video`, `hailuo_video`, `kling_video`, `runway_aleph_video`, `wan_animate`, `midjourney_generate` |
 | **Audio (3)** | `suno_generate_music`, `elevenlabs_tts`, `elevenlabs_ttsfx` |
-| **Utility (3)** | `list_tasks`, `get_task_status`, `veo3_get_1080p_video` |
+| **Utility (2)** | `list_tasks`, `get_task_status` |
 
 **→ [See complete tool documentation](docs/TOOLS.md)**
 
@@ -280,8 +257,8 @@ export KIE_AI_DISABLED_TOOLS="midjourney_generate,runway_aleph_video"
 **Priority Logic**: `ENABLED_TOOLS` > `TOOL_CATEGORIES` > `DISABLED_TOOLS` > All tools (default)
 
 **Tool Categories**:
-- **image** (8): nano_banana, seedream, qwen, openai_4o, flux, recraft, ideogram, midjourney*
-- **video** (9): veo3, veo3_1080p, sora, seedance, wan, hailuo, kling, runway, midjourney*
+- **image** (9): nano_banana, seedream, qwen, gpt_image_2, flux_kontext, flux2, topaz, recraft, ideogram, midjourney*
+- **video** (10): veo3, seedance, wan_video, happyhorse_video, hailuo, kling, runway, wan_animate, midjourney*
 - **audio** (3): suno, elevenlabs_tts, elevenlabs_ttsfx
 - **utility** (2): list_tasks, get_task_status ⭐ **Always enabled**
 
@@ -341,12 +318,11 @@ Or if installed globally with npx:
 ### Generate Video
 ```json
 {
-  "tool": "sora_video",
+  "tool": "wan_video",
   "arguments": {
     "prompt": "A peaceful garden with blooming flowers and butterflies",
-    "model": "sora-2",
     "resolution": "1080p",
-    "duration": "10"
+    "duration": 5
   }
 }
 ```
@@ -422,7 +398,7 @@ The server includes a built-in SQLite database for persistent task tracking:
 
 ```bash
 # Generate social media video content
-sora_video: "A trendy coffee shop with latte art, cinematic lighting"
+wan_video: "A trendy coffee shop with latte art, cinematic lighting"
 
 # Create product photography
 nano_banana_image: "Luxury watch on marble surface, professional product shot"
@@ -470,7 +446,7 @@ elevenlabs_tts: "Tap here to get started with your new profile"
 veo3_generate_video: "Professional office environment, employee training scenario"
 
 # Create corporate presentations
-openai_4o_image: "Add company logo to presentation slide, maintain professional style"
+gpt_image_2: "Add company logo to presentation slide, maintain professional style"
 
 # Produce marketing content
 suno_generate_music: "Corporate background music for promotional video"

package/dist/index.js

@@ -5,7 +5,7 @@ import { CallToolRequestSchema, ErrorCode, ListToolsRequestSchema, ListResources
 import { KieAiClient } from "./kie-ai-client.js";
 import { TaskDatabase } from "./database.js";
 import { z } from "zod";
-import { NanoBananaImageSchema, Veo3GenerateSchema, SunoGenerateSchema, ElevenLabsTTSSchema, ElevenLabsSoundEffectsSchema, ByteDanceSeedanceVideoSchema, ByteDanceSeedreamImageSchema, QwenImageSchema, RunwayAlephVideoSchema, Wan27VideoSchema, MidjourneyGenerateSchema, GptImage2Schema, FluxKontextImageSchema, RecraftRemoveBackgroundSchema, IdeogramReframeSchema, KlingVideoSchema, HailuoVideoSchema, SoraVideoSchema, Flux2ImageSchema, WanAnimateSchema, ZImageSchema, GrokImagineSchema, InfiniTalkSchema, KlingAvatarSchema, TopazUpscaleImageSchema, HappyHorseVideoSchema, } from "./types.js";
+import { NanoBananaImageSchema, Veo3GenerateSchema, SunoGenerateSchema, ElevenLabsTTSSchema, ElevenLabsSoundEffectsSchema, ByteDanceSeedanceVideoSchema, ByteDanceSeedreamImageSchema, QwenImageSchema, RunwayAlephVideoSchema, Wan27VideoSchema, MidjourneyGenerateSchema, GptImage2Schema, FluxKontextImageSchema, RecraftRemoveBackgroundSchema, IdeogramReframeSchema, KlingVideoSchema, HailuoVideoSchema, Flux2ImageSchema, WanAnimateSchema, ZImageSchema, GrokImagineSchema, InfiniTalkSchema, KlingAvatarSchema, TopazUpscaleImageSchema, HappyHorseVideoSchema, } from "./types.js";
 class KieAiMcpServer {
     server;
     client;
@@ -29,7 +29,6 @@ class KieAiMcpServer {
         video: [
             "veo3_generate_video",
             "veo3_get_1080p_video",
-            "sora_video",
             "bytedance_seedance_video",
             "wan_video",
             "wan_animate",
@@ -54,7 +53,7 @@ class KieAiMcpServer {
     constructor() {
         this.server = new Server({
             name: "kie-ai-mcp-server",
-            version: "3.2.0",
+            version: "3.2.1",
         });
         // Initialize client with config from environment
         this.config = {
@@ -1921,56 +1920,6 @@ class KieAiMcpServer {
                         required: ["prompt"],
                     },
                 },
-                {
-                    name: "sora_video",
-                    description: "Generate videos using OpenAI's Sora 2 models (unified tool for text-to-video, image-to-video, and storyboard generation with standard/high quality)",
-                    inputSchema: {
-                        type: "object",
-                        properties: {
-                            prompt: {
-                                type: "string",
-                                description: "Text prompt describing the desired video content (max 5000 characters). Required for text-to-video and image-to-video modes, optional for storyboard mode.",
-                                maxLength: 5000,
-                            },
-                            image_urls: {
-                                type: "array",
-                                description: "Array of image URLs for image-to-video or storyboard modes (1-10 URLs). For storyboard mode: provide images without prompt. For image-to-video: provide with prompt.",
-                                items: { type: "string", format: "uri" },
-                                minItems: 1,
-                                maxItems: 10,
-                            },
-                            aspect_ratio: {
-                                type: "string",
-                                description: "Aspect ratio of the generated video",
-                                enum: ["portrait", "landscape"],
-                                default: "landscape",
-                            },
-                            n_frames: {
-                                type: "string",
-                                description: "Number of frames/duration: 10s (5fps), 15s (5fps), or 25s (5fps). Storyboard mode supports 15s and 25s only.",
-                                enum: ["10", "15", "25"],
-                                default: "10",
-                            },
-                            size: {
-                                type: "string",
-                                description: "Quality tier: standard (480p) or high (1080p). High quality uses pro endpoints.",
-                                enum: ["standard", "high"],
-                                default: "standard",
-                            },
-                            remove_watermark: {
-                                type: "boolean",
-                                description: "Whether to remove the Sora watermark from the generated video",
-                                default: true,
-                            },
-                            callBackUrl: {
-                                type: "string",
-                                description: "Optional: URL for task completion notifications (uses KIE_AI_CALLBACK_URL env var if not provided)",
-                                format: "uri",
-                            },
-                        },
-                        required: [],
-                    },
-                },
             ];
             const filteredTools = allTools.filter((tool) => this.enabledTools.has(tool.name));
             return { tools: filteredTools };
@@ -2035,8 +1984,6 @@ class KieAiMcpServer {
                         return await this.handleKlingVideo(args);
                     case "hailuo_video":
                         return await this.handleHailuoVideo(args);
-                    case "sora_video":
-                        return await this.handleSoraVideo(args);
                     case "flux2_image":
                         return await this.handleFlux2Image(args);
                     case "wan_animate":
@@ -2189,26 +2136,6 @@ class KieAiMcpServer {
                             priority: 0.6,
                         },
                     },
-                    {
-                        uri: "kie://models/sora-2",
-                        name: "Sora 2 Standard",
-                        description: "OpenAI Sora 2 text/image/storyboard video (480p, secondary option)",
-                        mimeType: "text/markdown",
-                        annotations: {
-                            audience: ["assistant"],
-                            priority: 0.7,
-                        },
-                    },
-                    {
-                        uri: "kie://models/sora-2-pro",
-                        name: "Sora 2 Pro",
-                        description: "OpenAI Sora 2 premium quality video (1080p, secondary option)",
-                        mimeType: "text/markdown",
-                        annotations: {
-                            audience: ["assistant"],
-                            priority: 0.7,
-                        },
-                    },
                     {
                         uri: "kie://models/midjourney",
                         name: "Midjourney",
@@ -2758,9 +2685,6 @@ class KieAiMcpServer {
                     "veo3",
                     "veo3-fast",
                     "veo3-1080p",
-                    "sora-video",
-                    "sora-2",
-                    "sora-2-pro",
                     "kling-3.0-video",
                     "bytedance-seedance-video",
                     "wan-video",
@@ -4498,82 +4422,6 @@ class KieAiMcpServer {
             });
         }
     }
-    async handleSoraVideo(args) {
-        try {
-            const request = SoraVideoSchema.parse(args);
-            request.callBackUrl = this.getCallbackUrl(request.callBackUrl);
-            const response = await this.client.generateSoraVideo(request);
-            let modeDescription;
-            if (!request.prompt && request.image_urls?.length) {
-                modeDescription = `storyboard (${request.size || "standard"} quality)`;
-            }
-            else if (request.prompt && !request.image_urls?.length) {
-                modeDescription = `text-to-video (${request.size || "standard"} quality)`;
-            }
-            else if (request.prompt && request.image_urls?.length) {
-                modeDescription = `image-to-video (${request.size || "standard"} quality)`;
-            }
-            else {
-                modeDescription = `unknown mode`;
-            }
-            if (response.data?.taskId) {
-                await this.db.createTask({
-                    task_id: response.data.taskId,
-                    api_type: "sora-video",
-                    status: "pending",
-                });
-            }
-            return {
-                content: [
-                    {
-                        type: "text",
-                        text: JSON.stringify({
-                            success: true,
-                            task_id: response.data?.taskId,
-                            mode: modeDescription,
-                            message: `Sora video generation task created successfully (${modeDescription})`,
-                            parameters: {
-                                prompt: request.prompt,
-                                image_urls: request.image_urls,
-                                aspect_ratio: request.aspect_ratio || "landscape",
-                                n_frames: request.n_frames || "10",
-                                size: request.size || "standard",
-                                remove_watermark: request.remove_watermark !== false,
-                                callBackUrl: request.callBackUrl,
-                            },
-                            next_steps: [
-                                "Use get_task_status to check generation progress",
-                                "Task completion will be sent to the provided callback URL",
-                                "Video generation typically takes 2-5 minutes for standard, 5-10 minutes for high quality",
-                            ],
-                        }, null, 2),
-                    },
-                ],
-            };
-        }
-        catch (error) {
-            if (error instanceof z.ZodError) {
-                return this.formatError("sora_video", error, {
-                    prompt: "Optional: text description for video generation (max 5000 chars). Required for text-to-video and image-to-video modes.",
-                    image_urls: "Optional: array of image URLs for image-to-video or storyboard modes (1-10 URLs)",
-                    aspect_ratio: 'Optional: aspect ratio "portrait" or "landscape" (default: landscape)',
-                    n_frames: 'Optional: number of frames "10" (default), "15", or "25". Storyboard mode supports 15s and 25s only.',
-                    size: 'Optional: quality tier "standard" (default) or "high"',
-                    remove_watermark: "Optional: remove Sora watermark (default: true)",
-                    callBackUrl: "Optional: callback URL for notifications (uses KIE_AI_CALLBACK_URL env var if not provided)",
-                });
-            }
-            return this.formatError("sora_video", error, {
-                prompt: "Optional: text description for video generation",
-                image_urls: "Optional: array of image URLs for image-to-video or storyboard modes",
-                aspect_ratio: "Optional: aspect ratio (portrait or landscape)",
-                n_frames: "Optional: video duration in frames (10, 15, or 25)",
-                size: "Optional: quality tier (standard or high)",
-                remove_watermark: "Optional: remove Sora watermark",
-                callBackUrl: "Optional: URL for task completion notifications",
-            });
-        }
-    }
     async handleFlux2Image(args) {
         try {
             const request = Flux2ImageSchema.parse(args);
@@ -5356,8 +5204,6 @@ These guidelines ensure optimal balance between quality requirements and cost ma
             "kling-v2-5": "kling_v2-5-turbo-text-to-video-pro.md",
             midjourney: "midjourney_generate.md",
             hailuo: "hailuo_02-text-to-video-pro.md",
-            "sora-2": "sora-2-text-to-video.md",
-            "sora-2-pro": "sora-2-pro-text-to-video.md",
         };
         const fileName = modelFiles[modelKey];
         if (!fileName) {

package/dist/kie-ai-client.d.ts

@@ -1,4 +1,4 @@
-import { KieAiConfig, KieAiResponse, NanoBananaImageRequest, Veo3GenerateRequest, SunoGenerateRequest, ElevenLabsTTSRequest, ElevenLabsSoundEffectsRequest, ByteDanceSeedanceVideoRequest, RunwayAlephVideoRequest, WanVideoRequest, ByteDanceSeedreamImageRequest, QwenImageRequest, MidjourneyGenerateRequest, GptImage2Request, FluxKontextImageRequest, RecraftRemoveBackgroundRequest, IdeogramReframeRequest, KlingVideoRequest, HailuoVideoRequest, SoraVideoRequest, Flux2ImageRequest, WanAnimateRequest, ZImageRequest, GrokImagineRequest, InfiniTalkRequest, KlingAvatarRequest, TopazUpscaleImageRequest, HappyHorseVideoRequest, ImageResponse, TaskResponse } from "./types.js";
+import { KieAiConfig, KieAiResponse, NanoBananaImageRequest, Veo3GenerateRequest, SunoGenerateRequest, ElevenLabsTTSRequest, ElevenLabsSoundEffectsRequest, ByteDanceSeedanceVideoRequest, RunwayAlephVideoRequest, WanVideoRequest, ByteDanceSeedreamImageRequest, QwenImageRequest, MidjourneyGenerateRequest, GptImage2Request, FluxKontextImageRequest, RecraftRemoveBackgroundRequest, IdeogramReframeRequest, KlingVideoRequest, HailuoVideoRequest, Flux2ImageRequest, WanAnimateRequest, ZImageRequest, GrokImagineRequest, InfiniTalkRequest, KlingAvatarRequest, TopazUpscaleImageRequest, HappyHorseVideoRequest, ImageResponse, TaskResponse } from "./types.js";
 export declare class KieAiClient {
     private config;
     constructor(config: KieAiConfig);
@@ -23,7 +23,6 @@ export declare class KieAiClient {
     getVeo1080pVideo(taskId: string, index?: number): Promise<KieAiResponse<any>>;
     generateKlingVideo(request: KlingVideoRequest): Promise<KieAiResponse<TaskResponse>>;
     generateHailuoVideo(request: HailuoVideoRequest): Promise<KieAiResponse<TaskResponse>>;
-    generateSoraVideo(request: SoraVideoRequest): Promise<KieAiResponse<TaskResponse>>;
     generateFlux2Image(request: Flux2ImageRequest): Promise<KieAiResponse<TaskResponse>>;
     generateWanAnimate(request: WanAnimateRequest): Promise<KieAiResponse<TaskResponse>>;
     generateZImage(request: ZImageRequest): Promise<KieAiResponse<TaskResponse>>;

package/dist/kie-ai-client.js

@@ -82,7 +82,6 @@ export class KieAiClient {
             apiType === "ideogram-reframe" ||
             apiType === "kling-3.0-video" ||
             apiType === "hailuo" ||
-            apiType === "sora-video" ||
             apiType === "flux2-image" ||
             apiType === "wan-animate" ||
             apiType === "topaz-upscale" ||
@@ -636,62 +635,6 @@ export class KieAiClient {
         };
         return this.makeRequest("/jobs/createTask", "POST", jobRequest);
     }
-    async generateSoraVideo(request) {
-        // Smart mode detection based on parameters
-        const hasPrompt = !!request.prompt;
-        const hasImages = !!request.image_urls?.length;
-        let model;
-        let input;
-        if (!hasPrompt && hasImages) {
-            // Storyboard mode: images only, no prompt
-            model = "openai/sora-2-storyboard";
-            input = {
-                image_urls: request.image_urls,
-                aspect_ratio: request.aspect_ratio || "landscape",
-                n_frames: request.n_frames || "15", // Storyboard defaults to 15s
-                size: request.size || "standard",
-                remove_watermark: request.remove_watermark !== false,
-            };
-        }
-        else if (hasPrompt && !hasImages) {
-            // Text-to-video mode
-            const isHighQuality = request.size === "high";
-            model = isHighQuality
-                ? "openai/sora-2-pro-text-to-video"
-                : "openai/sora-2-text-to-video";
-            input = {
-                prompt: request.prompt,
-                aspect_ratio: request.aspect_ratio || "landscape",
-                n_frames: request.n_frames || "10",
-                size: request.size || "standard",
-                remove_watermark: request.remove_watermark !== false,
-            };
-        }
-        else if (hasPrompt && hasImages) {
-            // Image-to-video mode
-            const isHighQuality = request.size === "high";
-            model = isHighQuality
-                ? "openai/sora-2-pro-image-to-video"
-                : "openai/sora-2-image-to-video";
-            input = {
-                prompt: request.prompt,
-                image_urls: request.image_urls,
-                aspect_ratio: request.aspect_ratio || "landscape",
-                n_frames: request.n_frames || "10",
-                size: request.size || "standard",
-                remove_watermark: request.remove_watermark !== false,
-            };
-        }
-        else {
-            throw new Error("Invalid parameters: must provide either prompt (for text-to-video) or image_urls (for storyboard), or both (for image-to-video)");
-        }
-        const jobRequest = {
-            model,
-            input,
-            callBackUrl: request.callBackUrl || process.env.KIE_AI_CALLBACK_URL,
-        };
-        return this.makeRequest("/jobs/createTask", "POST", jobRequest);
-    }
     async generateFlux2Image(request) {
         // Smart mode detection based on parameters
         const hasInputUrls = !!request.input_urls && request.input_urls.length > 0;

package/dist/types.d.ts

@@ -1167,48 +1167,6 @@ export declare const HailuoVideoSchema: z.ZodEffects<z.ZodObject<{
     promptOptimizer?: boolean | undefined;
 }>;
 export type HailuoVideoRequest = z.infer<typeof HailuoVideoSchema>;
-export declare const SoraVideoSchema: z.ZodEffects<z.ZodObject<{
-    prompt: z.ZodOptional<z.ZodString>;
-    image_urls: z.ZodOptional<z.ZodArray<z.ZodString, "many">>;
-    aspect_ratio: z.ZodOptional<z.ZodDefault<z.ZodEnum<["portrait", "landscape"]>>>;
-    n_frames: z.ZodOptional<z.ZodDefault<z.ZodEnum<["10", "15", "25"]>>>;
-    size: z.ZodOptional<z.ZodDefault<z.ZodEnum<["standard", "high"]>>>;
-    remove_watermark: z.ZodOptional<z.ZodDefault<z.ZodBoolean>>;
-    callBackUrl: z.ZodOptional<z.ZodString>;
-}, "strip", z.ZodTypeAny, {
-    prompt?: string | undefined;
-    aspect_ratio?: "portrait" | "landscape" | undefined;
-    callBackUrl?: string | undefined;
-    image_urls?: string[] | undefined;
-    n_frames?: "10" | "15" | "25" | undefined;
-    size?: "standard" | "high" | undefined;
-    remove_watermark?: boolean | undefined;
-}, {
-    prompt?: string | undefined;
-    aspect_ratio?: "portrait" | "landscape" | undefined;
-    callBackUrl?: string | undefined;
-    image_urls?: string[] | undefined;
-    n_frames?: "10" | "15" | "25" | undefined;
-    size?: "standard" | "high" | undefined;
-    remove_watermark?: boolean | undefined;
-}>, {
-    prompt?: string | undefined;
-    aspect_ratio?: "portrait" | "landscape" | undefined;
-    callBackUrl?: string | undefined;
-    image_urls?: string[] | undefined;
-    n_frames?: "10" | "15" | "25" | undefined;
-    size?: "standard" | "high" | undefined;
-    remove_watermark?: boolean | undefined;
-}, {
-    prompt?: string | undefined;
-    aspect_ratio?: "portrait" | "landscape" | undefined;
-    callBackUrl?: string | undefined;
-    image_urls?: string[] | undefined;
-    n_frames?: "10" | "15" | "25" | undefined;
-    size?: "standard" | "high" | undefined;
-    remove_watermark?: boolean | undefined;
-}>;
-export type SoraVideoRequest = z.infer<typeof SoraVideoSchema>;
 export declare const Flux2ImageSchema: z.ZodEffects<z.ZodObject<{
     prompt: z.ZodString;
     input_urls: z.ZodOptional<z.ZodArray<z.ZodString, "many">>;
@@ -1281,7 +1239,7 @@ export interface TaskResponse {
 export interface TaskRecord {
     id?: number;
     task_id: string;
-    api_type: "nano-banana" | "nano-banana-edit" | "nano-banana-image" | "veo3" | "suno" | "elevenlabs-tts" | "elevenlabs-sound-effects" | "bytedance-seedance-video" | "runway-aleph-video" | "wan-video" | "bytedance-seedream-image" | "qwen-image" | "midjourney" | "gpt-image-2" | "flux-kontext-image" | "recraft-remove-background" | "ideogram-reframe" | "kling-3.0-video" | "hailuo" | "sora-video" | "flux2-image" | "wan-animate" | "z-image" | "grok-imagine" | "infinitalk" | "kling-avatar" | "topaz-upscale" | "happyhorse-video";
+    api_type: "nano-banana" | "nano-banana-edit" | "nano-banana-image" | "veo3" | "suno" | "elevenlabs-tts" | "elevenlabs-sound-effects" | "bytedance-seedance-video" | "runway-aleph-video" | "wan-video" | "bytedance-seedream-image" | "qwen-image" | "midjourney" | "gpt-image-2" | "flux-kontext-image" | "recraft-remove-background" | "ideogram-reframe" | "kling-3.0-video" | "hailuo" | "flux2-image" | "wan-animate" | "z-image" | "grok-imagine" | "infinitalk" | "kling-avatar" | "topaz-upscale" | "happyhorse-video";
     status: "pending" | "processing" | "completed" | "failed";
     created_at: string;
     updated_at: string;

package/dist/types.js

@@ -770,45 +770,6 @@ export const HailuoVideoSchema = z
     message: "Invalid parameter combination. Choose mode: 1) prompt only (text-to-video), or 2) prompt + imageUrl (image-to-video). endImageUrl is only valid with imageUrl. For 2.3: 10s+1080P not supported, 512P not available. For 02: 1080P not available.",
     path: [],
 });
-// Sora Video - Unified tool for all 5 Sora 2 endpoints
-export const SoraVideoSchema = z
-    .object({
-    prompt: z.string().min(1).max(5000).optional(),
-    image_urls: z.array(z.string().url()).min(1).max(10).optional(),
-    aspect_ratio: z
-        .enum(["portrait", "landscape"])
-        .default("landscape")
-        .optional(),
-    n_frames: z.enum(["10", "15", "25"]).default("10").optional(),
-    size: z.enum(["standard", "high"]).default("standard").optional(),
-    remove_watermark: z.boolean().default(true).optional(),
-    callBackUrl: z.string().url().optional(),
-})
-    .refine((data) => {
-    // Smart mode validation based on input parameters
-    const hasPrompt = !!data.prompt;
-    const hasImages = !!data.image_urls?.length;
-    // Storyboard mode: no prompt required, but images required
-    if (!hasPrompt && !hasImages) {
-        return false; // Need either prompt or images
-    }
-    // Storyboard mode: images only, no prompt
-    if (!hasPrompt && hasImages) {
-        return data.n_frames !== "10"; // Storyboard supports 15s, 25s (not 10s)
-    }
-    // Text-to-video mode: prompt only, no images
-    if (hasPrompt && !hasImages) {
-        return true; // All parameters valid
-    }
-    // Image-to-video mode: prompt + images
-    if (hasPrompt && hasImages) {
-        return true; // All parameters valid
-    }
-    return true;
-}, {
-    message: "Invalid parameter combination. For storyboard mode: provide image_urls without prompt. For text-to-video: provide prompt only. For image-to-video: provide both prompt and image_urls.",
-    path: [],
-});
 // Flux-2 Image - Unified text-to-image and image-to-image (Pro/Flex)
 export const Flux2ImageSchema = z
     .object({

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@felores/kie-ai-mcp-server",
-  "version": "3.2.0",
-  "description": "MCP server for Kie.ai APIs (25 AI tools: Nano Banana image generation/editing/upscaling, Veo3 video generation, Suno music generation, ElevenLabs TTS/sound effects, ByteDance Seedance/Seedream video/image, Qwen image generation/editing, Runway Aleph video transformation, Midjourney AI generation, Wan 2.7 video generation, Hailuo video generation, Kling video generation, GPT Image 2 generation/editing, Flux Kontext image generation/editing, Recraft background removal, Ideogram image reframing, Sora 2 video generation, Topaz image upscaling, HappyHorse 1.0 video generation)",
+  "version": "3.2.1",
+  "description": "MCP server for Kie.ai APIs (24 AI tools: Nano Banana image generation/editing/upscaling, Veo3 video generation, Suno music generation, ElevenLabs TTS/sound effects, ByteDance Seedance/Seedream video/image, Qwen image generation/editing, Runway Aleph video transformation, Midjourney AI generation, Wan 2.7 video generation, Hailuo video generation, Kling video generation, GPT Image 2 generation/editing, Flux Kontext image generation/editing, Recraft background removal, Ideogram image reframing, Topaz image upscaling, HappyHorse 1.0 video generation)",
   "main": "dist/index.js",
   "bin": {
     "kie-ai-mcp-server": "dist/index.js"