このMCPでできること
Generates and transforms images, video, speech, music, sound effects, and text through a catalog of AI models, with asynchronous result retrieval.
ツール
入力スキーマ
{'type': 'object', 'required': ['model_id', 'messages'], 'properties': {'n': {'type': 'integer', 'default': 1, 'description': 'Number of completions to generate (1-10).'}, 'seed': {'type': 'integer', 'description': 'Random seed for reproducible results.'}, 'stop': {'type': 'array', 'description': 'Up to 4 sequences where the API will stop generating.'}, 'top_k': {'type': 'integer', 'description': 'Top-k sampling parameter.'}, 'top_p': {'type': 'number', 'description': 'Nucleus sampling parameter (0-1).'}, 'plugins': {'type': 'array', 'description': 'OpenRouter plugins. Send [{"id":"file-parser","pdf":{"engine":"native"}}] alongside a {"type":"file"} content part to have a PDF attachment parsed.'}, 'messages': {'type': 'array', 'description': 'Array of message objects with "role" (system/user/assistant) and "content" keys.'}, 'model_id': {'type': 'string', 'description': 'The LLM model ID to use (e.g., "gpt-4", "claude-3").'}, 'max_tokens': {'type': 'integer', 'description': 'Maximum number of tokens to generate.'}, 'temperature': {'type': 'number', 'default': 1, 'description': 'Sampling temperature (0-2). Higher values make output more random.'}, 'response_format': {'type': 'object', 'description': 'Response format configuration (e.g., {"type": "json_object"}).'}, 'presence_penalty': {'type': 'number', 'description': 'Penalty for new topics (-2 to 2).'}, 'frequency_penalty': {'type': 'number', 'description': 'Penalty for frequent tokens (-2 to 2).'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'init_video', 'source_lang', 'output_lang'], 'properties': {'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when dubbing completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for dubbing.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_video': {'type': 'string', 'description': 'URL or base64 string of the video to dub.'}, 'output_lang': {'type': 'string', 'description': 'Target language code for the dubbed output.'}, 'source_lang': {'type': 'string', 'description': 'Source language code (e.g., "en", "es", "fr").'}}}
入力スキーマ
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'integer', 'description': 'The request ID returned from a previous audio generation call.'}}}
入力スキーマ
{'type': 'object', 'required': ['id', 'type'], 'properties': {'id': {'type': 'integer', 'description': 'The numeric id returned by a generation tool when status was "processing".'}, 'type': {'enum': ['images', 'videos', 'audios'], 'type': 'string', 'description': 'The generation category matching the original request: "images" for image tools, "videos" for video tools, "audios" for audio tools.'}}}
入力スキーマ
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'integer', 'description': 'The request ID returned from a previous image generation call.'}}}
入力スキーマ
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'The request ID returned from a previous video generation call.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'prompt', 'init_image'], 'properties': {'width': {'type': 'integer', 'description': 'Output image width in pixels (512-1024).'}, 'height': {'type': 'integer', 'description': 'Output image height in pixels (512-1024).'}, 'prompt': {'type': 'string', 'description': 'Text description of how to transform the image.'}, 'samples': {'type': 'integer', 'default': 1, 'description': 'Number of images to generate (1-4).'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for image transformation.'}, 'strength': {'type': 'number', 'description': 'Transformation strength (0-1). Higher values mean more change from the original.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_image': {'type': 'string', 'description': 'Input image URL or base64 string to transform.'}, 'aspect_ratio': {'type': 'string', 'description': 'Aspect ratio for the output image.'}, 'negative_prompt': {'type': 'string', 'description': 'Text describing what to avoid in the output.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'init_image'], 'properties': {'prompt': {'type': 'string', 'description': 'Text description of the video motion/transformation.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'duration': {'type': 'integer', 'description': 'Video duration in seconds (minimum 4).'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for video generation.'}, 'portrait': {'type': 'boolean', 'description': 'Generate in portrait orientation.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_audio': {'type': 'string', 'description': 'URL of audio to sync with the video.'}, 'init_image': {'type': 'string', 'description': 'Input image URL or base64 string to animate.'}, 'resolution': {'type': 'string', 'description': 'Output resolution preset.'}, 'aspect_ratio': {'type': 'string', 'description': 'Aspect ratio for the video.'}, 'negative_prompt': {'type': 'string', 'description': 'Things to avoid in the generated video.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'prompt', 'init_image', 'mask_image'], 'properties': {'prompt': {'type': 'string', 'description': 'Text description of what to paint in the masked area.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for inpainting.'}, 'strength': {'type': 'number', 'description': 'Strength of the transformation (0-1). Higher values mean more change.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_image': {'type': 'string', 'description': 'URL or base64 string of the input image to edit.'}, 'mask_image': {'type': 'string', 'description': 'URL or base64 string of the mask image (white areas will be edited, black areas preserved).'}, 'negative_prompt': {'type': 'string', 'description': 'Things to avoid in the generated content.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'init_video', 'init_audio'], 'properties': {'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when processing completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for lip sync.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_audio': {'type': 'string', 'description': 'URL or base64 string of the audio file to sync lips with.'}, 'init_video': {'type': 'string', 'description': 'URL or base64 string of the input video containing the face to sync.'}}}
入力スキーマ
{'type': 'object', 'properties': {'nsfw': {'type': 'boolean', 'description': 'Set to false to exclude NSFW models, true to include them. Defaults to user preference.'}, 'sort': {'type': 'string', 'default': 'recommended', 'description': 'Sort order: "recommended" (default), "latest", "most-used".'}, 'limit': {'type': 'integer', 'default': 20, 'description': 'Maximum number of models to return (1-100).'}, 'search': {'type': 'string', 'description': 'Search models by name, ID, description, or tags.'}, 'feature': {'type': 'string', 'description': 'Filter by product feature: "imagen" (images), "videofusion" (videos), "audiogen" (audio/voice), "llmaster" (LLMs), "threedverse" (3D).'}, 'category': {'type': 'string', 'description': 'Filter by model category (e.g., "stable_diffusion", "stable_diffusion_xl", "flux", "llm", "video", "voice_cloning").'}, 'provider': {'enum': ['alibaba_cloud', 'bfl', 'byteplus', 'elevenlabs', 'google', 'groq', 'higgsfield', 'inworld', 'klingai', 'ltx', 'minimax', 'modelslab', 'mulerouter', 'open_router', 'openai', 'recraft', 'runway_ml', 'skyreels', 'sonauto', 'sync', 'tencent', 'together_ai', 'vidu', 'xai', 'zoho'], 'type': 'string', 'description': 'Filter by model provider (e.g., "modelslab", "civitai").'}, 'subcategory': {'type': 'string', 'description': 'Filter by model subcategory (e.g., "lora", "controlnet", "embeddings", "checkpoint").'}}}
入力スキーマ
{'type': 'object', 'properties': {'feature': {'type': 'string', 'description': 'Filter providers by product feature: "imagen" (images), "videofusion" (videos), "audiogen" (audio/voice), "llmaster" (LLMs), "threedverse" (3D).'}, 'category': {'type': 'string', 'description': 'Filter providers by model category (e.g., "stable_diffusion", "flux", "llm", "video").'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'init_image', 'init_video', 'character_orientation'], 'properties': {'mode': {'enum': ['std', 'pro'], 'type': 'string', 'description': 'Processing mode: std (standard) or pro (professional).'}, 'prompt': {'type': 'string', 'description': 'Optional text prompt (max 2500 characters).'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when processing completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for motion control.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_image': {'type': 'string', 'description': 'URL or base64 string of the input image (character/subject).'}, 'init_video': {'type': 'string', 'description': 'URL or base64 string of the video for motion reference.'}, 'keep_original_sound': {'enum': ['yes', 'no'], 'type': 'string', 'description': 'Keep original sound from the video.'}, 'character_orientation': {'enum': ['image', 'video'], 'type': 'string', 'description': 'Use character orientation from image or video.'}}}
入力スキーマ
{'type': 'object', 'required': ['prompt', 'model_id'], 'properties': {'tags': {'type': 'array', 'description': 'Array of genre/style tags for the music.'}, 'lyrics': {'type': 'string', 'description': 'Lyrics to include in the generated song.'}, 'prompt': {'type': 'string', 'description': 'Text description of the music to generate.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for music generation.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'music_length_ms': {'type': 'number', 'description': 'Duration of the music in milliseconds.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'init_audio', 'side'], 'properties': {'side': {'enum': ['left', 'right'], 'type': 'string', 'description': 'Which side to extend: left (beginning) or right (end).'}, 'tags': {'type': 'array', 'description': 'Array of genre/style tags.'}, 'lyrics': {'type': 'string', 'description': 'Lyrics for the extended portion.'}, 'prompt': {'type': 'string', 'description': 'Optional text description for the extended portion.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when extension completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for song extension.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_audio': {'type': 'string', 'description': 'URL or base64 string of the audio file to extend.'}, 'crop_duration': {'type': 'number', 'description': 'Duration to crop from the original.'}, 'extend_duration': {'type': 'number', 'description': 'Duration to extend in seconds.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'init_audio', 'sections'], 'properties': {'tags': {'type': 'array', 'description': 'Array of genre/style tags.'}, 'lyrics': {'type': 'string', 'description': 'Lyrics for the regenerated section.'}, 'prompt': {'type': 'string', 'description': 'Optional text description for the regenerated section.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when inpainting completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for song inpainting.'}, 'sections': {'type': 'array', 'description': 'Array of 2 numbers: [start_time, end_time] in seconds for the section to regenerate.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_audio': {'type': 'string', 'description': 'URL or base64 string of the audio file to edit.'}, 'instrumental': {'type': 'boolean', 'description': 'Generate instrumental only (no vocals).'}, 'selection_crop': {'type': 'boolean', 'description': 'Return only the regenerated section.'}}}
入力スキーマ
{'type': 'object', 'required': ['prompt', 'model_id'], 'properties': {'prompt': {'type': 'string', 'description': 'Text description of the sound effect to generate.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'duration': {'type': 'integer', 'description': 'Duration of the sound effect in seconds.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for sound generation.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}}}
入力スキーマ
{'type': 'object', 'required': ['init_audio', 'model_id', 'voice_id'], 'properties': {'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when conversion completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for voice conversion.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'voice_id': {'type': 'string', 'description': 'The target voice ID to convert to.'}, 'init_audio': {'type': 'string', 'description': 'URL or base64 string of the audio file to transform.'}}}
入力スキーマ
{'type': 'object', 'required': ['init_audio', 'model_id'], 'properties': {'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when transcription completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for speech-to-text.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_audio': {'type': 'string', 'description': 'URL or base64 string of the audio file to transcribe.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'prompt'], 'properties': {'width': {'type': 'integer', 'default': 1024, 'description': 'Image width in pixels (512-1024).'}, 'height': {'type': 'integer', 'default': 1024, 'description': 'Image height in pixels (512-1024).'}, 'prompt': {'type': 'string', 'description': 'Text description of the image to generate.'}, 'samples': {'type': 'integer', 'default': 1, 'description': 'Number of images to generate (1-4).'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for image generation (e.g., "flux-dev", "sdxl").'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'aspect_ratio': {'type': 'string', 'description': 'Aspect ratio for the image (e.g., "1:1", "16:9", "9:16").'}, 'negative_prompt': {'type': 'string', 'description': 'Text describing what to avoid in the image.'}}}
入力スキーマ
{'type': 'object', 'required': ['prompt', 'voice_id', 'model_id'], 'properties': {'prompt': {'type': 'string', 'description': 'The text to convert to speech.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for text-to-speech.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'voice_id': {'type': 'string', 'description': 'The voice ID to use for speech generation.'}, 'temperature': {'type': 'number', 'description': 'Temperature for voice variation (0-1).'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'prompt'], 'properties': {'fps': {'type': 'integer', 'description': 'Frames per second for the output video.'}, 'width': {'type': 'integer', 'description': 'Video width in pixels (512-1024).'}, 'height': {'type': 'integer', 'description': 'Video height in pixels (512-1024).'}, 'prompt': {'type': 'string', 'description': 'Text description of the video to generate.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'duration': {'type': 'integer', 'description': 'Video duration in seconds (minimum 4).'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for video generation.'}, 'portrait': {'type': 'boolean', 'description': 'Generate in portrait orientation.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_audio': {'type': 'string', 'description': 'URL of audio to sync with the video.'}, 'resolution': {'type': 'string', 'description': 'Output resolution preset.'}, 'aspect_ratio': {'type': 'string', 'description': 'Aspect ratio for the video (e.g., "16:9", "9:16").'}, 'camera_fixed': {'type': 'boolean', 'description': 'Keep camera position fixed during generation.'}, 'enhance_prompt': {'type': 'boolean', 'description': 'Use AI to enhance the prompt.'}, 'generate_audio': {'type': 'boolean', 'description': 'Generate audio for the video.'}, 'negative_prompt': {'type': 'string', 'description': 'Things to avoid in the generated video.'}}}
入力スキーマ
{'type': 'object', 'required': ['model_id', 'prompt', 'init_video'], 'properties': {'seed': {'type': 'integer', 'description': 'Random seed for reproducible results (0-4294967295).'}, 'prompt': {'type': 'string', 'description': 'Text description of how to transform the video.'}, 'webhook': {'type': 'string', 'description': 'URL to receive webhook notification when generation completes.'}, 'duration': {'type': 'integer', 'description': 'Video duration in seconds (minimum 4).'}, 'model_id': {'type': 'string', 'description': 'The model ID to use for video transformation.'}, 'track_id': {'type': 'string', 'description': 'Custom tracking ID for the request.'}, 'init_image': {'type': 'array', 'description': 'Optional guidance image URLs applied in order across the input video.'}, 'init_video': {'type': 'string', 'description': 'Input video URL to transform.'}, 'aspect_ratio': {'type': 'string', 'description': 'Aspect ratio for the output video.'}, 'negative_prompt': {'type': 'string', 'description': 'Things to avoid in the generated video.'}, 'image_timestamps': {'type': 'array', 'description': 'Optional seconds into the video where each init_image applies, in the same order. Images without a timestamp are spread evenly across the clip.'}, 'public_figure_threshold': {'enum': ['auto', 'low', 'medium', 'high'], 'type': 'string', 'description': 'Threshold for public figure detection.'}}}
最近のツール変更
類似のMCPサーバー
MiOffice — AI-Powered Workspace Studio
Provides browser-based tools for processing PDFs, images, video, and audio, including generation, enhancement, conversion, transc…
BlitzReels Video Editor
Creates and edits short-form videos, including timelines, captions, transitions, AI-generated visuals, music, voiceovers, sound e…
Morpha
Enables creating, animating, and exporting layered short-form video projects.
switch
Enables management and exploration of an account-scoped library of AI-generated images and videos.
Magnific
Provides image enhancement and design tools, AI image and audio generation, text-to-speech, creation management, and reusable cre…
Uwear
Supports AI fashion photoshoot production with garments, outfits, avatars, locations, art direction, image generation, backdrops,…
aicut
Generates and analyzes AI videos, images, audio, talking-avatar clips, scripted stories, and social posts, with staged review and…
Creative Claw
Generates and edits branded images, video, audio, speech, and 3D-related creative assets, with media processing and reusable them…