What this MCP does
Provides access to text, image, video, music, lyric-generation, image-editing, and image-upscaling models through a unified API.
Tools
Input schema
{'type': 'object', 'required': ['model', 'messages'], 'properties': {'stop': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Up to 4 sequences that stop generation.'}, 'model': {'type': 'string', 'description': "Exact model name, e.g. claude-sonnet-5 or deepseek-v4-pro. Call list_models with category 'text' if unsure."}, 'top_p': {'type': ['null', 'number'], 'description': 'Nucleus sampling probability mass, 0-1. Omit for the model default.'}, 'messages': {'type': ['null', 'array'], 'items': {'type': 'object', 'required': ['role', 'content'], 'properties': {'role': {'type': 'string', 'description': 'Message author: system, user or assistant.'}, 'content': {'type': 'string', 'description': 'Message text.'}}, 'additionalProperties': False}, 'description': 'Conversation so far, oldest first. Must contain at least one message.'}, 'max_tokens': {'type': ['null', 'integer'], 'description': 'Maximum tokens to generate. Omit for the model default.'}, 'temperature': {'type': ['null', 'number'], 'description': 'Sampling temperature, typically 0-2. Omit for the model default.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['content', 'model', 'usage'], 'properties': {'model': {'type': 'string', 'description': 'Model that actually served the request.'}, 'usage': {'type': 'object', 'required': ['prompt_tokens', 'completion_tokens', 'total_tokens'], 'properties': {'total_tokens': {'type': 'integer', 'description': 'Prompt plus completion tokens.'}, 'prompt_tokens': {'type': 'integer', 'description': 'Tokens consumed by the prompt.'}, 'completion_tokens': {'type': 'integer', 'description': 'Tokens generated.'}}, 'description': 'Token accounting for this call.', 'additionalProperties': False}, 'content': {'type': 'string', 'description': "The model's reply text."}, 'finish_reason': {'type': 'string', 'description': 'Why generation stopped, e.g. stop or length.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['model', 'prompt'], 'properties': {'n': {'type': ['null', 'integer'], 'description': 'How many images to generate. Defaults to 1. Each one is billed.'}, 'size': {'type': 'string', 'description': "Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default."}, 'async': {'type': 'boolean', 'description': "Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'."}, 'model': {'type': 'string', 'description': "Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure."}, 'images': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references.'}, 'prompt': {'type': 'string', 'description': 'Description of the image to generate.'}, 'quality': {'type': 'string', 'description': 'Quality hint, e.g. low, medium, high or auto. Model-dependent.'}, 'aspect_ratio': {'type': 'string', 'description': 'Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16.'}, 'nsfw_checker': {'type': ['null', 'boolean'], 'description': 'Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time.'}, 'response_format': {'type': 'string', 'description': "'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['model', 'status'], 'properties': {'note': {'type': 'string', 'description': 'What to do next.'}, 'model': {'type': 'string', 'description': 'Model that served the request.'}, 'images': {'type': ['null', 'array'], 'items': {'type': 'object', 'properties': {'url': {'type': 'string', 'description': 'Link to the generated image. May expire; download anything worth keeping.'}, 'b64_json': {'type': 'string', 'description': 'Base64 image data, when response_format was b64_json.'}, 'revised_prompt': {'type': 'string', 'description': 'The prompt the model actually used, when it rewrote the input.'}}, 'additionalProperties': False}, 'description': 'Generated images, when the call completed.'}, 'status': {'type': 'string', 'description': 'One of: completed, queued, in_progress, failed.'}, 'task_id': {'type': 'string', 'description': 'Task identifier, when submitted asynchronously and still running.'}, 'platform': {'type': 'string', 'description': 'Pass this to get_task together with task_id.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['clip_id', 'continue_at'], 'properties': {'tags': {'type': 'string', 'description': 'Style tags for the extension.'}, 'title': {'type': 'string', 'description': 'New title for the extended song.'}, 'prompt': {'type': 'string', 'description': 'Lyrics for the extended section.'}, 'clip_id': {'type': 'string', 'description': "ID of the song to extend, taken from the 'raw' clip list of a completed generate_music task."}, 'provider': {'type': 'string', 'description': "Music backend: 'suno' (default) or 'producer'."}, 'continue_at': {'type': 'number', 'description': 'Timestamp in seconds within the original song to continue from.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Poll server-side for up to this many seconds (max 240).'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['task_id', 'platform', 'status', 'note'], 'properties': {'raw': {'description': 'Full result payload when completed — clip IDs, lyrics text and per-clip metadata. Clip IDs from here are what extend_music takes.'}, 'note': {'type': 'string', 'description': 'What to do next.'}, 'status': {'type': 'string', 'description': 'One of: queued, in_progress, completed, failed.'}, 'task_id': {'type': 'string', 'description': 'Pass this to get_task together with platform to check progress.'}, 'platform': {'type': 'string', 'description': "'suno' or 'producer'. Pass to get_task."}, 'audio_urls': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Finished audio URLs, when the task completed within wait_seconds.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['model', 'prompt'], 'properties': {'n': {'type': ['null', 'integer'], 'description': 'How many images to generate. Defaults to 1. Each one is billed.'}, 'size': {'type': 'string', 'description': "Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default."}, 'async': {'type': 'boolean', 'description': "Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'."}, 'model': {'type': 'string', 'description': "Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure."}, 'images': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references.'}, 'prompt': {'type': 'string', 'description': 'Description of the image to generate.'}, 'quality': {'type': 'string', 'description': 'Quality hint, e.g. low, medium, high or auto. Model-dependent.'}, 'aspect_ratio': {'type': 'string', 'description': 'Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16.'}, 'nsfw_checker': {'type': ['null', 'boolean'], 'description': 'Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time.'}, 'response_format': {'type': 'string', 'description': "'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['model', 'status'], 'properties': {'note': {'type': 'string', 'description': 'What to do next.'}, 'model': {'type': 'string', 'description': 'Model that served the request.'}, 'images': {'type': ['null', 'array'], 'items': {'type': 'object', 'properties': {'url': {'type': 'string', 'description': 'Link to the generated image. May expire; download anything worth keeping.'}, 'b64_json': {'type': 'string', 'description': 'Base64 image data, when response_format was b64_json.'}, 'revised_prompt': {'type': 'string', 'description': 'The prompt the model actually used, when it rewrote the input.'}}, 'additionalProperties': False}, 'description': 'Generated images, when the call completed.'}, 'status': {'type': 'string', 'description': 'One of: completed, queued, in_progress, failed.'}, 'task_id': {'type': 'string', 'description': 'Task identifier, when submitted asynchronously and still running.'}, 'platform': {'type': 'string', 'description': 'Pass this to get_task together with task_id.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['prompt'], 'properties': {'prompt': {'type': 'string', 'description': "Description of the lyrics to write, e.g. 'a love song about meeting someone at a coffee shop'."}, 'provider': {'type': 'string', 'description': "Music backend: 'suno' (default) or 'producer'."}, 'lyrics_model': {'type': 'string', 'description': 'Lyrics model: classic or remi.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Poll server-side for up to this many seconds (max 240). Lyrics usually finish in under 30 seconds.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['task_id', 'platform', 'status', 'note'], 'properties': {'raw': {'description': 'Full result payload when completed — clip IDs, lyrics text and per-clip metadata. Clip IDs from here are what extend_music takes.'}, 'note': {'type': 'string', 'description': 'What to do next.'}, 'status': {'type': 'string', 'description': 'One of: queued, in_progress, completed, failed.'}, 'task_id': {'type': 'string', 'description': 'Pass this to get_task together with platform to check progress.'}, 'platform': {'type': 'string', 'description': "'suno' or 'producer'. Pass to get_task."}, 'audio_urls': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Finished audio URLs, when the task completed within wait_seconds.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['prompt'], 'properties': {'tags': {'type': 'string', 'description': "Comma-separated style tags, e.g. 'pop, upbeat, guitar'. Max 200 characters."}, 'model': {'type': 'string', 'description': 'Suno model version, e.g. chirp-v5 or chirp-v4-5-plus. Omit for the platform default.'}, 'title': {'type': 'string', 'description': 'Song title. Used in custom mode.'}, 'custom': {'type': 'boolean', 'description': 'false (default) lets the model write the lyrics from your description; true means prompt contains lyrics you wrote and you should also set title and tags.'}, 'prompt': {'type': 'string', 'description': "In simple mode (custom=false) a description of the song, e.g. 'a dreamy lo-fi track about late-night trains'. In custom mode (custom=true) the actual lyrics, with section markers like [Verse] and [Chorus]."}, 'provider': {'type': 'string', 'description': "Music backend: 'suno' (default) or 'producer'."}, 'instrumental': {'type': 'boolean', 'description': 'Generate without vocals.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Poll server-side for up to this many seconds (max 240) and return finished audio if it completes in time. Omit to return a task_id immediately.'}, 'negative_tags': {'type': 'string', 'description': "Styles to avoid, e.g. 'heavy metal, rap'."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['task_id', 'platform', 'status', 'note'], 'properties': {'raw': {'description': 'Full result payload when completed — clip IDs, lyrics text and per-clip metadata. Clip IDs from here are what extend_music takes.'}, 'note': {'type': 'string', 'description': 'What to do next.'}, 'status': {'type': 'string', 'description': 'One of: queued, in_progress, completed, failed.'}, 'task_id': {'type': 'string', 'description': 'Pass this to get_task together with platform to check progress.'}, 'platform': {'type': 'string', 'description': "'suno' or 'producer'. Pass to get_task."}, 'audio_urls': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Finished audio URLs, when the task completed within wait_seconds.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['model', 'prompt'], 'properties': {'model': {'type': 'string', 'description': "Exact model name, e.g. doubao-seedance-2-0-260128, veo-3.1-quality or viduq3-pro. Call list_models with category 'video' if unsure."}, 'ratio': {'type': 'string', 'description': 'Aspect ratio, e.g. 16:9, 9:16, 1:1, 21:9 or adaptive. Which values a model accepts varies; an unsupported one is rejected with a message naming the valid ones.'}, 'audios': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Optional Seedance reference audio URLs or asset:// URIs returned by the trusted asset catalog. Reference audio cannot be used alone.'}, 'images': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Optional reference image URLs. A single image is used as the first frame; use image_roles to control multiple.'}, 'prompt': {'type': 'string', 'description': 'Description of the video to generate.'}, 'videos': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Optional Seedance reference video URLs or asset:// URIs returned by the trusted asset catalog.'}, 'duration': {'type': ['null', 'integer'], 'description': 'Clip length in seconds. Model-dependent, typically 4-15; an unsupported value is rejected with a message naming the supported ones. Omit for the model default.'}, 'resolution': {'type': 'string', 'description': 'Output resolution: 480p, 720p (widest compatibility) or 1080p. Model-dependent.'}, 'image_roles': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Role of each entry in images, positionally: first_frame, last_frame or reference_image.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Poll server-side for up to this many seconds (max 240) and return the finished video if it completes in time. Omit to return a task_id immediately.'}, 'generate_audio': {'type': ['null', 'boolean'], 'description': 'Generate a synchronised soundtrack. Only some models support this.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['task_id', 'platform', 'status', 'model', 'note'], 'properties': {'note': {'type': 'string', 'description': 'What to do next.'}, 'model': {'type': 'string', 'description': 'Model that accepted the request.'}, 'status': {'type': 'string', 'description': 'One of: queued, in_progress, completed, failed.'}, 'task_id': {'type': 'string', 'description': 'Pass this to get_task together with platform to check progress.'}, 'platform': {'type': 'string', 'description': "Always 'video'. Pass to get_task."}, 'video_urls': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Finished video URLs, when the task completed within wait_seconds.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['unlimited', 'used_amount', 'currency'], 'properties': {'note': {'type': 'string', 'description': 'Guidance when the balance is low, unlimited, or scoped to a token.'}, 'currency': {'type': 'string', 'description': 'Unit of the amounts above, e.g. USD.'}, 'unlimited': {'type': 'boolean', 'description': 'True when this token has no spending cap, in which case the amount fields are not meaningful.'}, 'used_amount': {'type': 'number', 'description': 'Balance consumed to date, in the same unit.'}, 'total_amount': {'type': 'number', 'description': 'Remaining plus used. Omitted when unlimited.'}, 'remaining_amount': {'type': 'number', 'description': "Remaining balance, in the account's display currency. Omitted when unlimited."}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['platform', 'task_id'], 'properties': {'task_id': {'type': 'string', 'description': 'Task identifier returned by the submit tool.'}, 'platform': {'type': 'string', 'description': 'Platform the task belongs to, exactly as returned by the submit tool: image, video, suno or producer.'}, 'wait_seconds': {'type': ['null', 'integer'], 'description': 'Poll server-side for up to this many seconds (max 240) and return once the task finishes. Omit for a single immediate status check.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['task_id', 'platform', 'status'], 'properties': {'raw': {'description': 'Backend payload, for details this summary does not cover (lyrics text, per-clip metadata, seeds).'}, 'note': {'type': 'string', 'description': 'What to do next.'}, 'status': {'type': 'string', 'description': 'One of: queued, in_progress, completed, failed, unknown.'}, 'task_id': {'type': 'string', 'description': 'The task this status refers to.'}, 'platform': {'type': 'string', 'description': 'Platform the task belongs to.'}, 'progress': {'type': 'string', 'description': 'Progress indication, when the backend reports one.'}, 'fail_reason': {'type': 'string', 'description': 'Why the task failed, when status is failed.'}, 'result_urls': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Finished asset URLs. May expire; download anything worth keeping.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'properties': {'search': {'type': 'string', 'description': "Case-insensitive substring match on the model name, e.g. 'claude' or 'seedance'."}, 'category': {'type': 'string', 'description': 'Filter by capability. One of: text, image, video, music, embedding, other. Omit to list every model this key can use.'}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['models', 'total'], 'properties': {'note': {'type': 'string', 'description': 'Guidance about the result set.'}, 'total': {'type': 'integer', 'description': 'Number of models returned.'}, 'models': {'type': ['null', 'array'], 'items': {'type': 'object', 'required': ['name', 'category'], 'properties': {'name': {'type': 'string', 'description': 'The exact model name to pass to other tools.'}, 'tool': {'type': 'string', 'description': 'Which MCP tool to call for this model. Absent means no MCP tool drives it — reach it through the REST API instead.'}, 'groups': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'Token groups that can reach this model.'}, 'vendor': {'type': 'string', 'description': 'Upstream vendor, e.g. Anthropic, Google, Suno.'}, 'category': {'type': 'string', 'description': 'Capability category: text, image, video, music, embedding or other.'}, 'endpoints': {'type': ['null', 'array'], 'items': {'type': 'string'}, 'description': 'API endpoint families this model supports.'}, 'description': {'type': 'string', 'description': 'Human-readable description, when the platform publishes one.'}}, 'additionalProperties': False}, 'description': 'Models available to the calling key.'}}, 'additionalProperties': False}
Input schema
{'type': 'object', 'required': ['image'], 'properties': {'image': {'type': 'string', 'description': 'The image to upscale, as an HTTPS URL, data URL, or raw base64. Width and height must each be 256-1024 px and the file at most 5 MB.'}, 'model_quality': {'type': 'string', 'description': 'Upscale quality hint: HQ, MQ (default) or LQ.'}, 'response_format': {'type': 'string', 'description': "'url' (default) or 'b64_json'."}}, 'additionalProperties': False}
Output schema
{'type': 'object', 'required': ['model', 'status'], 'properties': {'note': {'type': 'string', 'description': 'What to do next.'}, 'model': {'type': 'string', 'description': 'Model that served the request.'}, 'images': {'type': ['null', 'array'], 'items': {'type': 'object', 'properties': {'url': {'type': 'string', 'description': 'Link to the generated image. May expire; download anything worth keeping.'}, 'b64_json': {'type': 'string', 'description': 'Base64 image data, when response_format was b64_json.'}, 'revised_prompt': {'type': 'string', 'description': 'The prompt the model actually used, when it rewrote the input.'}}, 'additionalProperties': False}, 'description': 'Generated images, when the call completed.'}, 'status': {'type': 'string', 'description': 'One of: completed, queued, in_progress, failed.'}, 'task_id': {'type': 'string', 'description': 'Task identifier, when submitted asynchronously and still running.'}, 'platform': {'type': 'string', 'description': 'Pass this to get_task together with task_id.'}}, 'additionalProperties': False}
Recent tool changes
Similar MCP servers
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…