이 MCP로 할 수 있는 일
Searches and retrieves CC0 images and supports AI image, video, resizing, and upscaling workflows.
도구
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['context', 'llm_model'], 'properties': {'tier': {'type': 'string', 'maxLength': 24, 'description': 'Tier key from list_models (e.g. 720p, 1080p, 720p-audio)'}, 'model': {'type': 'string', 'maxLength': 64, 'description': 'Video model id from list_models (default: Veo 3.1 Fast)'}, 'prompt': {'type': 'string', 'maxLength': 2000, 'description': 'Required unless start_image is given'}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'start_image': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, {'type': 'string', 'maxLength': 64, 'minLength': 1}], 'description': 'Animate from this image (stock id or your edited image id)'}, 'aspect_ratio': {'enum': ['9:16', '4:5', '3:4', '2:3', '1:1', '3:2', '4:3', '5:4', '16:9'], 'type': 'string', 'description': 'Text-to-video only; a start image sets the ratio'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}, 'negative_prompt': {'type': 'string', 'maxLength': 1000}, 'duration_seconds': {'type': 'integer', 'maximum': 30, 'minimum': 1, 'description': "Clip length; must be one of the model's durations"}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['job_id', 'status', 'video', 'credits_charged'], 'properties': {'video': {'type': 'object', 'required': ['url', 'duration_seconds'], 'properties': {'url': {'type': 'string'}, 'duration_seconds': {'type': ['number', 'null']}}, 'additionalProperties': False}, 'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'completed'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['job_id', 'status', 'credits_charged', 'message'], 'properties': {'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'pending'}, 'message': {'type': 'string'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id', 'context', 'llm_model'], 'properties': {'id': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, {'type': 'string', 'pattern': '^\\d+$'}], 'description': 'Stock image id or your own edited image id'}, 'format': {'enum': ['jpg', 'png'], 'type': 'string', 'description': 'Default jpg (the original)'}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['id', 'title', 'url', 'format', 'dimensions', 'license', 'page_url'], 'properties': {'id': {'type': 'number'}, 'url': {'type': 'string'}, 'title': {'type': 'string'}, 'format': {'type': 'string'}, 'license': {'type': 'object', 'required': ['license', 'license_url', 'public_domain', 'commercial_use', 'attribution_required', 'restrictions'], 'properties': {'license': {'type': 'string'}, 'license_url': {'type': 'string'}, 'restrictions': {'type': 'array', 'items': {'type': 'string'}}, 'public_domain': {'type': 'boolean'}, 'commercial_use': {'type': 'boolean'}, 'attribution_required': {'type': 'boolean'}}, 'additionalProperties': False}, 'page_url': {'type': 'string'}, 'dimensions': {'anyOf': [{'type': 'object', 'required': ['width', 'height'], 'properties': {'width': {'type': 'number'}, 'height': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'null'}]}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id', 'context', 'llm_model'], 'properties': {'id': {'type': 'integer', 'maximum': 9007199254740991, 'description': 'Numeric image id from a previous result', 'exclusiveMinimum': 0}, 'page': {'type': 'integer', 'maximum': 5, 'minimum': 1, 'description': 'Page number, 1-5'}, 'limit': {'type': 'integer', 'maximum': 12, 'minimum': 1, 'description': 'Results to return, 1-12 (default 12). Ask for fewer to save tokens.'}, 'locale': {'enum': ['en', 'de', 'es', 'fa', 'fr', 'it', 'ja', 'pt'], 'type': 'string', 'description': 'Site locale for the user (default en). Titles and page links are localized; descriptions are English.'}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['results', 'page', 'total_results', 'total_pages', 'has_more', 'license_note'], 'properties': {'page': {'type': 'number'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'preview_url', 'page_url', 'aspect_ratio', 'dimensions', 'tags'], 'properties': {'id': {'type': 'number'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'page_url': {'type': 'string'}, 'dimensions': {'anyOf': [{'type': 'object', 'required': ['width', 'height'], 'properties': {'width': {'type': 'number'}, 'height': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'null'}], 'description': 'Full-resolution pixel size; null when unknown'}, 'description': {'type': 'string'}, 'preview_url': {'type': 'string'}, 'aspect_ratio': {'type': 'string', 'description': 'e.g. "16:9", "9:16", "1:1"'}}, 'additionalProperties': False}}, 'has_more': {'type': 'boolean'}, 'refinements': {'type': 'object', 'required': ['mood', 'style'], 'properties': {'mood': {'type': 'array', 'items': {'type': 'string'}}, 'style': {'type': 'array', 'items': {'type': 'string'}}}, 'description': 'Exact mood/style facet values available for this query â\x80\x94 pass one back as `mood` / `style` to narrow', 'additionalProperties': False}, 'total_pages': {'type': 'number'}, 'license_note': {'type': 'string'}, 'total_results': {'type': 'number'}}, 'additionalProperties': False}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['prompt', 'context', 'llm_model'], 'properties': {'tier': {'type': 'string', 'maxLength': 16, 'description': "Tier key from list_models (e.g. 1k, 2k, standard). Default: the model's default tier."}, 'model': {'type': 'string', 'maxLength': 64, 'description': 'Model id from list_models. Default: the site default for subscribers, the free model otherwise.'}, 'prompt': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'aspect_ratio': {'enum': ['9:16', '4:5', '3:4', '2:3', '1:1', '3:2', '4:3', '5:4', '16:9'], 'type': 'string'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}, 'reference_images': {'type': 'array', 'items': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, {'type': 'string', 'maxLength': 64, 'minLength': 1}], 'description': 'A StockCake image id (from search_images), one of your own edited image ids (from a previous result), or a job_id. Never a URL.'}, 'maxItems': 9, 'description': 'Stock image ids or your own edited image ids used as references'}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['job_id', 'status', 'image', 'credits_charged'], 'properties': {'image': {'type': 'object', 'required': ['id', 'url'], 'properties': {'id': {'type': ['number', 'null'], 'description': 'Edited image id â\x80\x94 pass it to download_image or as an image reference'}, 'url': {'type': 'string'}}, 'additionalProperties': False}, 'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'completed'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['job_id', 'status', 'credits_charged', 'message'], 'properties': {'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'pending'}, 'message': {'type': 'string'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['context', 'llm_model'], 'properties': {'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['plan', 'tier', 'is_entitled', 'balance', 'next_reset', 'max_download_multiplier', 'formats', 'upgrade_url'], 'properties': {'plan': {'type': 'string'}, 'tier': {'type': ['string', 'null']}, 'balance': {'type': 'object', 'required': ['total', 'free', 'subscription', 'purchased'], 'properties': {'free': {'type': 'number'}, 'total': {'type': 'number'}, 'purchased': {'type': 'number'}, 'subscription': {'type': 'number'}}, 'additionalProperties': False}, 'formats': {'type': 'array', 'items': {'type': 'string'}}, 'next_reset': {'type': 'object', 'required': ['free', 'subscription'], 'properties': {'free': {'type': ['string', 'null']}, 'subscription': {'type': ['string', 'null']}}, 'additionalProperties': False}, 'is_entitled': {'type': 'boolean'}, 'upgrade_url': {'type': 'string'}, 'max_download_multiplier': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id', 'context', 'llm_model'], 'properties': {'id': {'anyOf': [{'type': 'integer', 'maximum': 2147483647, 'exclusiveMinimum': 0}, {'type': 'string', 'maxLength': 64, 'minLength': 4}], 'description': "Numeric image id (from search results) or the image's CDN uuid"}, 'locale': {'enum': ['en', 'de', 'es', 'fa', 'fr', 'it', 'ja', 'pt'], 'type': 'string', 'description': 'Site locale for the user (default en). Titles and page links are localized; descriptions are English.'}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}, 'include_preview': {'type': 'boolean', 'description': 'Default true. Set false to skip the inline preview image and save tokens.'}}}
출력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['id', 'title', 'description', 'dimensions', 'tags', 'provenance', 'license', 'page_url', 'preview_url', 'attribution'], 'properties': {'id': {'type': 'number'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'license': {'type': 'object', 'required': ['license', 'license_url', 'public_domain', 'commercial_use', 'attribution_required', 'restrictions'], 'properties': {'license': {'type': 'string'}, 'license_url': {'type': 'string'}, 'restrictions': {'type': 'array', 'items': {'type': 'string'}}, 'public_domain': {'type': 'boolean'}, 'commercial_use': {'type': 'boolean'}, 'attribution_required': {'type': 'boolean'}}, 'additionalProperties': False}, 'page_url': {'type': 'string'}, 'dimensions': {'anyOf': [{'type': 'object', 'required': ['width', 'height'], 'properties': {'width': {'type': 'number'}, 'height': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'null'}], 'description': 'Full-resolution pixel size; null when unknown'}, 'provenance': {'type': 'object', 'required': ['ai_generated', 'prompt', 'style', 'generated_at', 'published_at', 'descriptive_attributes'], 'properties': {'style': {'type': ['string', 'null']}, 'prompt': {'type': ['string', 'null']}, 'ai_generated': {'type': 'boolean', 'const': True}, 'generated_at': {'type': ['string', 'null']}, 'published_at': {'type': ['string', 'null']}, 'descriptive_attributes': {'anyOf': [{'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, {'type': 'null'}]}}, 'additionalProperties': False}, 'attribution': {'type': 'object', 'required': ['markdown', 'html', 'plain'], 'properties': {'html': {'type': 'string'}, 'plain': {'type': 'string'}, 'markdown': {'type': 'string'}}, 'additionalProperties': False}, 'description': {'type': ['string', 'null']}, 'preview_url': {'type': 'string'}}, 'additionalProperties': False}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['job_id', 'context', 'llm_model'], 'properties': {'job_id': {'type': 'string', 'maxLength': 64, 'minLength': 8}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['job_id', 'status'], 'properties': {'error': {'type': 'object', 'required': ['message', 'refunded'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}, 'refunded': {'type': 'boolean'}}, 'additionalProperties': False}, 'job_id': {'type': 'string'}, 'result': {'type': 'object', 'properties': {'image_url': {'type': 'string'}, 'video_url': {'type': 'string'}, 'edited_image_id': {'type': 'number'}}, 'additionalProperties': False}, 'status': {'enum': ['pending', 'completed', 'error'], 'type': 'string'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['context', 'llm_model'], 'properties': {'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['context', 'llm_model'], 'properties': {'kind': {'enum': ['image', 'video'], 'type': 'string', 'description': 'Return only one catalog'}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'properties': {'image': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'name', 'provider', 'description', 'default', 'free', 'default_tier', 'tiers', 'supports_references', 'max_references'], 'properties': {'id': {'type': 'string'}, 'free': {'type': 'boolean'}, 'name': {'type': 'string'}, 'tiers': {'type': 'array', 'items': {'type': 'object', 'required': ['key', 'label', 'credits'], 'properties': {'key': {'type': 'string'}, 'label': {'type': 'string'}, 'credits': {'type': 'number'}, 'resolution': {'type': 'string'}}, 'additionalProperties': False}}, 'default': {'type': 'boolean'}, 'provider': {'type': 'string'}, 'description': {'type': 'string'}, 'default_tier': {'type': 'string'}, 'max_references': {'type': 'number'}, 'supports_references': {'type': 'boolean'}}, 'additionalProperties': False}}, 'video': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'name', 'provider', 'description', 'default', 'default_tier', 'tiers', 'durations', 'default_duration', 'image_to_video', 'aspect_ratios'], 'properties': {'id': {'type': 'string'}, 'name': {'type': 'string'}, 'tiers': {'type': 'array', 'items': {'type': 'object', 'required': ['key', 'resolution', 'audio', 'credits_per_second'], 'properties': {'key': {'type': 'string'}, 'audio': {'type': 'boolean'}, 'resolution': {'type': 'string'}, 'credits_per_second': {'type': 'number'}}, 'additionalProperties': False}}, 'default': {'type': 'boolean'}, 'provider': {'type': 'string'}, 'durations': {'type': 'array', 'items': {'type': 'number'}}, 'description': {'type': 'string'}, 'default_tier': {'type': 'string'}, 'aspect_ratios': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}]}, 'image_to_video': {'type': 'boolean'}, 'default_duration': {'type': 'number'}}, 'additionalProperties': False}}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['image', 'aspect_ratio', 'prompt', 'context', 'llm_model'], 'properties': {'image': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, {'type': 'string', 'maxLength': 64, 'minLength': 1}], 'description': 'A StockCake image id (from search_images), one of your own edited image ids (from a previous result), or a job_id. Never a URL.'}, 'prompt': {'type': 'string', 'maxLength': 2000, 'minLength': 1, 'description': "What should fill the extended canvas, e.g. 'extend the sandy beach and sky; keep the subject unchanged, do not crop or stretch'"}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'aspect_ratio': {'enum': ['9:16', '4:5', '3:4', '2:3', '1:1', '3:2', '4:3', '5:4', '16:9'], 'type': 'string', 'description': 'Target ratio'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['job_id', 'status', 'image', 'credits_charged'], 'properties': {'image': {'type': 'object', 'required': ['id', 'url'], 'properties': {'id': {'type': ['number', 'null'], 'description': 'Edited image id â\x80\x94 pass it to download_image or as an image reference'}, 'url': {'type': 'string'}}, 'additionalProperties': False}, 'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'completed'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['job_id', 'status', 'credits_charged', 'message'], 'properties': {'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'pending'}, 'message': {'type': 'string'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['query', 'context', 'llm_model'], 'properties': {'mood': {'type': 'string', 'maxLength': 50, 'description': 'Exact facet value â\x80\x94 pick one from refinements.mood of a previous search_images result'}, 'page': {'type': 'integer', 'maximum': 5, 'minimum': 1, 'description': 'Page number, 1-5'}, 'type': {'enum': ['photos', 'illustrations', 'digital-art', '3d'], 'type': 'string'}, 'color': {'type': 'string', 'maxLength': 30, 'description': 'Dominant color, e.g. a hex value like #ff0000'}, 'limit': {'type': 'integer', 'maximum': 12, 'minimum': 1, 'description': 'Results to return, 1-12 (default 12). Ask for fewer to save tokens.'}, 'query': {'type': 'string', 'maxLength': 300, 'minLength': 1, 'description': "Short subject, 2â\x80\x935 words (e.g. 'red vintage rocket'). Long sentences hurt recall: start short, add one qualifier at a time; if results are thin, drop keywords or rephrase."}, 'style': {'type': 'string', 'maxLength': 50, 'description': 'Exact facet value â\x80\x94 pick one from refinements.style of a previous search_images result'}, 'locale': {'enum': ['en', 'de', 'es', 'fa', 'fr', 'it', 'ja', 'pt'], 'type': 'string', 'description': 'Site locale for the user (default en). Titles and page links are localized; descriptions are English.'}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'orientation': {'enum': ['landscape', 'portrait', 'square'], 'type': 'string'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['results', 'page', 'total_results', 'total_pages', 'has_more', 'license_note'], 'properties': {'page': {'type': 'number'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'preview_url', 'page_url', 'aspect_ratio', 'dimensions', 'tags'], 'properties': {'id': {'type': 'number'}, 'tags': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'page_url': {'type': 'string'}, 'dimensions': {'anyOf': [{'type': 'object', 'required': ['width', 'height'], 'properties': {'width': {'type': 'number'}, 'height': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'null'}], 'description': 'Full-resolution pixel size; null when unknown'}, 'description': {'type': 'string'}, 'preview_url': {'type': 'string'}, 'aspect_ratio': {'type': 'string', 'description': 'e.g. "16:9", "9:16", "1:1"'}}, 'additionalProperties': False}}, 'has_more': {'type': 'boolean'}, 'refinements': {'type': 'object', 'required': ['mood', 'style'], 'properties': {'mood': {'type': 'array', 'items': {'type': 'string'}}, 'style': {'type': 'array', 'items': {'type': 'string'}}}, 'description': 'Exact mood/style facet values available for this query â\x80\x94 pass one back as `mood` / `style` to narrow', 'additionalProperties': False}, 'total_pages': {'type': 'number'}, 'license_note': {'type': 'string'}, 'total_results': {'type': 'number'}}, 'additionalProperties': False}
입력 스키마
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['image', 'scale', 'context', 'llm_model'], 'properties': {'image': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, {'type': 'string', 'maxLength': 64, 'minLength': 1}], 'description': 'A StockCake image id (from search_images), one of your own edited image ids (from a previous result), or a job_id. Never a URL.'}, 'scale': {'anyOf': [{'type': 'number', 'const': 2}, {'type': 'number', 'const': 4}, {'type': 'number', 'const': 8}]}, 'context': {'type': 'string', 'description': 'In one sentence, what is the user trying to make or find?'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" â\x80\x94 never guess.'}, 'conversation_id': {'type': 'string', 'description': "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call â\x80\x94 never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}}
출력 스키마
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['job_id', 'status', 'image', 'credits_charged'], 'properties': {'image': {'type': 'object', 'required': ['id', 'url'], 'properties': {'id': {'type': ['number', 'null'], 'description': 'Edited image id â\x80\x94 pass it to download_image or as an image reference'}, 'url': {'type': 'string'}}, 'additionalProperties': False}, 'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'completed'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['job_id', 'status', 'credits_charged', 'message'], 'properties': {'job_id': {'type': 'string'}, 'status': {'type': 'string', 'const': 'pending'}, 'message': {'type': 'string'}, 'credits_charged': {'type': 'number'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['code', 'message'], 'properties': {'code': {'type': 'string'}, 'message': {'type': 'string'}}, 'additionalProperties': {}}], '$schema': 'https://json-schema.org/draft/2020-12/schema'}
최근 도구 변경
유사한 MCP 서버
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.
framesail
Creates long-form YouTube videos through script generation, storyboarding, visual assets, voiceover, music, scene composition, an…
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,…
Creative Claw
Generates and edits branded images, video, audio, speech, and 3D-related creative assets, with media processing and reusable them…