Atlas Cloud MCP Server (Image / Video / LLM APIs)

Send a chat completion request to an LLM model via Atlas Cloud API (OpenAI-compatible format).

Args:

• model (string, required): The LLM model ID (e.g., "deepseek-ai/deepseek-v3.2", "qwen/qwen3-32b")
• messages (array, required): Array of message objects with "role" and "content" fields. Roles: "system", "user", "assistant"
• temperature (number, optional): Sampling temperature, 0-2. Default: 1
• max_tokens (number, optional): Maximum tokens in the response
• top_p (number, optional): Nucleus sampling parameter, 0-1. Default: 1

Returns: The LLM response including the generated message, token usage, and finish reason.

Examples:

• model="deepseek-ai/deepseek-v3.2", messages=[{"role": "user", "content": "Hello"}]
• model="qwen/qwen3-32b", messages=[{"role": "system", "content": "You are a helpful assistant"}, {"role": "user", "content": "Explain quantum computing"}], temperature=0.7

Generate audio — text-to-speech (TTS) AND music generation — using Atlas Cloud API.

This covers BOTH kinds of Audio-type models:

• TTS / voice models (e.g., "bytedance/seed-audio-1.0", "xai/tts-v1", ElevenLabs)
• Music / song models (e.g., "suno/chirp-v5", "minimax/music-2.6") — full songs with vocals, background music, jingles

This tool submits the generation request and returns immediately with a prediction ID. Use atlas_get_prediction to check the result later.

Parameters are validated against the model's schema BEFORE the request is submitted: if a parameter is missing, has the wrong type, or is not accepted, the tool returns a precise error and does NOT spend credits.

IMPORTANT: The "model" parameter requires an exact model ID (e.g., "bytedance/seed-audio-1.0"). If you don't know the exact model ID, you MUST first call atlas_list_models with type="Audio" to find it. Do NOT guess model IDs.

NOTE: For speech-to-text (transcription / ASR), use atlas_transcribe_audio instead.

You should also use atlas_get_model_info to see the full parameter list and schema for your chosen audio model before calling this tool. Different models accept different params (voice/speaker IDs, format, sample rate, speed, lyrics, style tags, etc.).

Args:

• model (string, required): The exact audio model ID. Use atlas_list_models with type="Audio" to find valid IDs.
• params (object, required): Model-specific parameters as a JSON object. For TTS the main field is usually "text" (the content to synthesize); for music models it is usually "prompt" and/or "lyrics". Use atlas_get_model_info to see available params.

Returns: A prediction ID to check the result with atlas_get_prediction. The output is an audio file URL.

Examples:

• model="bytedance/seed-audio-1.0", params={"text": "Welcome to Atlas Cloud."}
• model="bytedance/seed-audio-1.0", params={"text": "Hello there.", "format": "mp3", "sample_rate": 24000}
• model="suno/chirp-v5", params={"prompt": "upbeat synthwave song about coding at night"}
• model="minimax/music-2.6", params={"prompt": "gentle acoustic guitar background music"}

Generate an image using Atlas Cloud API. This also covers image-to-3D and text-to-3D models (they are Image-type models that return 3D files such as GLB/OBJ/USDZ).

This tool submits the generation request and returns immediately with a prediction ID. Use atlas_get_prediction to check the result later.

Parameters are validated against the model's schema BEFORE the request is submitted: if a parameter is missing, has the wrong type, or is not accepted, the tool returns a precise error and does NOT spend credits.

IMPORTANT: The "model" parameter requires an exact model ID (e.g., "seedream/seedream-v5.0-lite-text-to-image"). If you don't know the exact model ID, you MUST first call atlas_list_models with type="Image" to find it. Do NOT guess model IDs.

You should also use atlas_get_model_info to understand what parameters a specific image model accepts before calling this tool.

Args:

• model (string, required): The exact image model ID. Use atlas_list_models to find valid IDs.
• params (object, required): Model-specific parameters as a JSON object. Each model has different parameters defined in its schema. Common params include "prompt", "image_size", "num_inference_steps", etc. For image-to-3D models, "image" is required. Use atlas_get_model_info to see the full parameter list for your chosen model.

Returns: A prediction ID to check the result with atlas_get_prediction.

Examples:

• model="seedream/seedream-v5.0-lite-text-to-image", params={"prompt": "a cat in space"}
• model="qwen-image/qwen-image-text-to-image-plus", params={"prompt": "sunset over mountains", "image_size": "1024x1024"}
• model="tencent/hunyuan3d-rapid/image-to-3d", params={"image": "https://example.com/photo.jpg", "format": "GLB"}

Generate a video using Atlas Cloud API.

This tool submits the generation request and returns immediately with a prediction ID. Use atlas_get_prediction to check the result later.

Parameters are validated against the model's schema BEFORE the request is submitted: if a parameter is missing, has the wrong type, or is not accepted, the tool returns a precise error and does NOT spend credits.

IMPORTANT: The "model" parameter requires an exact model ID (e.g., "kling-video/kling-v3.0-standard-text-to-video"). If you don't know the exact model ID, you MUST first call atlas_list_models with type="Video" to find it. Do NOT guess model IDs.

You should also use atlas_get_model_info to see the full parameter list and schema for your chosen video model before calling this tool.

Args:

• model (string, required): The exact video model ID. Use atlas_list_models to find valid IDs.
• params (object, required): Model-specific parameters as a JSON object. Parameters vary by model - use atlas_get_model_info to see available params. Common ones include:
• "prompt" (string): Text description of the video
• "image_url" (string): Source image for image-to-video models
• "duration" (number): Video duration in seconds
• "aspect_ratio" (string): e.g., "16:9", "9:16"

Returns: A prediction ID to check the result with atlas_get_prediction. Video generation typically takes 1-5 minutes.

Examples:

• model="kling-video/kling-v3.0-standard-text-to-video", params={"prompt": "a rocket launching into space", "duration": 5}
• model="bytedance/seedance-v1.5-pro-image-to-video", params={"prompt": "camera panning right", "image_url": "https://example.com/photo.jpg"}

Get the current Atlas Cloud account balance and credit summary for the authenticated API key.

Returns available balance, cash, bonus, frozen amount, and credit grant status.

Args: None.

Examples:

• (no params) -> current account balance

Get daily model cost buckets (spend amount) for the authenticated API key over a UTC date range.

Omitting group_by returns total daily buckets. Use group_by to break costs down by model_type, model, and/or api_key.

Args:

• start_date (string, required): Inclusive UTC start date, YYYY-MM-DD.
• end_date (string, required): Exclusive UTC end date, YYYY-MM-DD (range <= 180 days).
• scope (string, optional): "self" (default) or "account".
• group_by (array, optional): Any of "model_type", "model", "api_key".
• model_types (array, optional): Filter by model type, e.g. ["text","image"].
• model_ids (array, optional): Filter by model ID (<= 100).
• limit (number, optional): Max grouped rows (1-1000, default 100).
• page (string, optional): Pagination cursor from a previous next_page.

Examples:

• start_date="2026-06-01", end_date="2026-07-01"
• start_date="2026-06-01", end_date="2026-07-01", group_by=["model"]

Get detailed information about a specific Atlas Cloud model, including API documentation, input/output schema, pricing, and usage examples.

This tool fetches the model's OpenAPI schema and generates comprehensive API documentation with cURL examples.

Args:

• model (string): The model ID (e.g., "deepseek-ai/deepseek-v3.2", "kling-video/kling-v3.0-standard-text-to-video")

Returns: Markdown-formatted model details including:

• Model metadata (type, provider, context length, etc.)
• Pricing information
• Full API input/output schema with parameter descriptions
• Required and optional parameters with defaults
• cURL usage examples
• Playground link

Examples:

• model="deepseek-ai/deepseek-v3.2" -> DeepSeek V3.2 model details and API docs
• model="kling-video/kling-v3.0-standard-text-to-video" -> Kling video model API docs

Get daily model usage buckets (requests, tokens, image/video counts) for the authenticated API key over a UTC date range.

Omitting group_by returns total daily buckets. Use group_by to break usage down by model_type, model, and/or api_key.

Args:

• start_date (string, required): Inclusive UTC start date, YYYY-MM-DD.
• end_date (string, required): Exclusive UTC end date, YYYY-MM-DD (range <= 180 days).
• scope (string, optional): "self" (default) or "account".
• group_by (array, optional): Any of "model_type", "model", "api_key".
• model_types (array, optional): Filter by model type, e.g. ["text","image"].
• model_ids (array, optional): Filter by model ID (<= 100).
• limit (number, optional): Max grouped rows (1-1000, default 100).
• page (string, optional): Pagination cursor from a previous next_page.

Examples:

• start_date="2026-06-01", end_date="2026-06-08"
• start_date="2026-06-01", end_date="2026-07-01", group_by=["model"]

Check the status and result of an image/video generation task.

Use this after submitting a generation request to check if the result is ready.

If the status is still "processing" or "starting", wait a moment and try again.

When the result is ready (status is "completed" or "succeeded"), the output URLs will be returned. You should then:

1. Show the output URLs to the user
2. Ask the user if they want to download the file to their local machine (you can use curl or wget to download it)

Args:

• prediction_id (string, required): The prediction ID returned from a generation request

Returns: The current status and output of the generation task.

Examples:

• prediction_id="pred_abc123" -> check generation status

List all available models on Atlas Cloud, optionally filtered by type.

Args:

• type (string, optional): Filter by model type. Options: "Text", "Image", "Video", "Audio"

Returns: Markdown-formatted list of models grouped by type, including model ID, description, provider, and pricing.

Note: image-to-3D and text-to-3D models are Image-type models (filter with type="Image"). Audio-type models (filter with type="Audio") include text-to-speech / TTS, music generation (e.g., Suno, MiniMax Music), and speech-to-text / ASR (e.g., Seed ASR). Lipsync / talking-avatar models are Video-type models.

Examples:

• No params -> list all models
• type="Image" -> list only image generation models (includes 3D)
• type="Video" -> list only video generation models (includes lipsync / talking-avatar)
• type="Text" -> list only LLM/text models
• type="Audio" -> list only audio models (TTS, music generation, speech-to-text/ASR)

One-step image, video, or audio generation - automatically finds the model by keyword, fetches its schema, builds parameters, and submits the task.

Covers all generation tasks: text-to-image, image editing, 3D (image/text-to-3D), text/image-to-video, lipsync & talking-avatar (video + audio_url), TTS, and music generation.

Parameters are validated against the model's schema BEFORE submitting. If extra_params contains fields the model does not accept (or wrong values), the tool returns a precise error and does NOT spend credits.

IMPORTANT: If this tool fails to find a model, call atlas_list_models first to get the exact model list, then use atlas_generate_image / atlas_generate_video / atlas_generate_audio with the exact model ID instead. Do NOT invent extra_params - only pass parameters you know the model accepts (check atlas_get_model_info).

The tool searches for models by keyword matching against model ID, display name, and tags. After getting the prediction ID, use atlas_get_prediction to check the result.

Args:

• model_keyword (string, required): A keyword to search for the model. Use the model's display name or key words (e.g., "Nano Banana", "Seedream", "Kling", "Vidu", "Seedance", "Seed Audio", "Suno", "Omni Human")
• type (string, required): Generation type: "Image", "Video", or "Audio"
• prompt (string, required): Text description of what to generate (for TTS, the text to synthesize; for music, the song description)
• image_url (string, optional): Source image URL for image-to-video, image editing, image-to-3D, or talking-avatar models
• audio_url (string, optional): Source audio URL for lipsync / talking-avatar video models (the speech the character should say) or speech-to-text models
• extra_params (object, optional): Additional model-specific parameters to override defaults (e.g., {"duration": 10, "aspect_ratio": "16:9"}). Only include parameters the model's schema accepts.

Returns: A prediction ID to check the result with atlas_get_prediction.

Examples:

• model_keyword="nano banana", type="Image", prompt="a cute cat in space"
• model_keyword="seedream v5", type="Image", prompt="sunset over mountains"
• model_keyword="kling v3", type="Video", prompt="a rocket launching", extra_params={"duration": 5}
• model_keyword="seedance", type="Video", prompt="camera panning right", image_url="https://example.com/photo.jpg"
• model_keyword="seed audio", type="Audio", prompt="Welcome to Atlas Cloud."
• model_keyword="suno", type="Audio", prompt="upbeat synthwave song about coding at night"
• model_keyword="omni human", type="Video", prompt="the person speaks to camera", image_url="https://example.com/portrait.jpg", audio_url="https://example.com/speech.mp3"

Search Atlas Cloud documentation, models, and API references by keyword.

Returns matching models with descriptions, pricing, and links. For detailed API docs of a specific model, use atlas_get_model_info instead.

Args:

• query (string): Search keyword to match against model names, types, providers, tags, etc.

Returns: Markdown-formatted list of matching models with key information.

Examples:

• "video generation" -> finds all video generation models
• "deepseek" -> finds all DeepSeek models
• "image edit" -> finds image editing models
• "qwen" -> finds all Qwen models

Transcribe speech audio to text (ASR / speech-to-text) using Atlas Cloud API.

Use this for: transcribing recordings, meetings, interviews, podcasts, voice notes; getting subtitles/captions text from audio.

This tool submits the transcription request and returns immediately with a prediction ID. Use atlas_get_prediction to check the result later — the output is the recognized text (some models also return timestamped utterances and speaker info).

Parameters are validated against the model's schema BEFORE the request is submitted: if a parameter is missing, has the wrong type, or is not accepted, the tool returns a precise error and does NOT spend credits.

IMPORTANT: The "model" parameter requires an exact speech-to-text model ID (e.g., "bytedance/seed-asr-2.0", "xai/stt-v1"). Speech-to-text models are Audio-type models — use atlas_list_models with type="Audio" to find them. Do NOT guess model IDs.

The audio must be reachable via URL. For local files, first call atlas_upload_media to get a URL.

Args:

• model (string, required): The exact speech-to-text model ID.
• params (object, required): Model-specific parameters. The main field is usually "audio_url" (URL of the audio to transcribe). Other common params: "language", "format", "enable_punc", "enable_speaker_info". Use atlas_get_model_info to see available params.

Returns: A prediction ID to check the result with atlas_get_prediction. The output is the transcribed text.

Examples:

• model="bytedance/seed-asr-2.0", params={"audio_url": "https://example.com/meeting.mp3"}
• model="bytedance/seed-asr-2.0", params={"audio_url": "https://example.com/interview.wav", "enable_speaker_info": true}

Upload a local image or media file to Atlas Cloud and get a publicly accessible URL.

Use this tool when you need to provide an image URL to image-editing or image-to-video models, but only have a local file path.

Workflow:

1. Upload the local file with this tool to get a URL
2. Use the returned URL as the "image_url" parameter in atlas_generate_image, atlas_generate_video, or atlas_quick_generate

Supported file types: images (jpg, png, webp, etc.), videos, and other media files.

IMPORTANT: This upload is intended for temporary use with Atlas Cloud generation tasks only. Uploaded files may be cleaned up periodically. Do NOT use this as a permanent file hosting service. Abuse (e.g., bulk uploads unrelated to generation tasks) may result in API key suspension.

Args:

• file_path (string, required): Absolute path to the local file to upload

Returns: The publicly accessible download URL of the uploaded file.

Examples:

• file_path="/Users/me/photos/cat.jpg" -> uploads and returns a URL like "https://atlas-img.oss-accelerate-overseas.aliyuncs.com/media/xxx.jpg"