Luw.ai

Official21 tools

by Luvi-io · TypeScript

AI interior, exterior and landscape design, photoreal rendering, image editing, video and 3D.

ai.luw/mcp Model Context Protocol (MCP) Server

The ai.luw/mcp server provides Model Context Protocol access to AI tools for interior, exterior, and landscape design, along with photoreal rendering, image editing, video, and 3D capabilities.

🛠️ Key Features

Interior design
Exterior design
Landscape design
Photoreal rendering
Image editing
Video
3D

🚀 Use Cases

Designing interior spaces
Planning exterior environments
Developing landscape concepts
Producing photoreal renderings
Editing images for design workflows
Generating or working with video content
Creating or viewing 3D assets

⚡ Developer Benefits

Supports design and media-related AI workflows via MCP
Exposes a set of capabilities centered on design, rendering, and content creation

⚠️ Limitations

Provided data includes only a high-level description; specific MCP tools, endpoints, or configuration details are not included.

Topics

ai-renderingarchitecturechatgptclaudegemini-cli-extensioninterior-designmcpmcp-servermodel-context-protocolreal-estatevirtual-staging

Captured live from the server via tools/list.

luw_interior_design

Redesign an interior photo — home, office, shop, hotel — in any style while keeping the room's architecture. Restyles furniture, materials, colors and lighting. Set empty_room=true to furnish an empty room or turn it into another room type (virtual staging). Costs 1 credit per variation.

Parameters14

image	string	required	Photo of the room (https:// URL, local file path, or data: URI).
prompt	string	optional	What you want, in plain language.
styles	array	optional	Design style names, e.g. ["Japandi"]. Case-sensitive; see luw_list_options.
room_type	string	optional	Room type, e.g. "Living Room", "Kitchen", "Bedroom", "Home Office" (see luw_list_options kind="interior_types").
empty_room	boolean	optional	Furnish from scratch / convert the room to room_type (Fill Empty Room mode).
style_reference	string	optional	Style-transfer source: an image whose look to copy (https:// URL, local file path, or data: URI), or "persona" to use slot 1 of persona_id.
reference_images	array	optional	Up to 6 reference images (furniture, materials, products, mood boards) to draw from.
precision	integer	optional	How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output image format.
variations	integer	optional	Number of alternative designs (1-4, default 1); each is billed as a generation.
persona_id	integer	optional	Persona whose saved images/knowledge to use (see luw_personas).

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Photo of the room (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What you want, in plain language.",
      "type": "string",
      "maxLength": 4000
    },
    "styles": {
      "description": "Design style names, e.g. [\"Japandi\"]. Case-sensitive; see luw_list_options.",
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "room_type": {
      "description": "Room type, e.g. \"Living Room\", \"Kitchen\", \"Bedroom\", \"Home Office\" (see luw_list_options kind=\"interior_types\").",
      "type": "string"
    },
    "empty_room": {
      "description": "Furnish from scratch / convert the room to room_type (Fill Empty Room mode).",
      "type": "boolean"
    },
    "style_reference": {
      "description": "Style-transfer source: an image whose look to copy (https:// URL, local file path, or data: URI), or \"persona\" to use slot 1 of persona_id.",
      "type": "string"
    },
    "reference_images": {
      "description": "Up to 6 reference images (furniture, materials, products, mood boards) to draw from.",
      "maxItems": 6,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "description": "Reference image (https:// URL, local file path, or data: URI)."
      }
    },
    "precision": {
      "description": "How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    },
    "variations": {
      "description": "Number of alternative designs (1-4, default 1); each is billed as a generation.",
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    },
    "persona_id": {
      "description": "Persona whose saved images/knowledge to use (see luw_personas).",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_exterior_design

Redesign a building exterior or facade photo — houses, villas, apartments, commercial buildings — in a new architectural style, with new materials, colors and landscaping, keeping the structure. Costs 1 credit per variation.

Parameters13

image	string	required	Photo of the building (https:// URL, local file path, or data: URI).
prompt	string	optional	What you want, in plain language.
styles	array	optional	Design style names, e.g. ["Japandi"]. Case-sensitive; see luw_list_options.
building_type	string	optional	Building/space type, e.g. "Modern House Exterior", "Luxury Villa Exterior", "Outdoor Patio" (see luw_list_options kind="exterior_types").
style_reference	string	optional	Style-transfer source: an image whose look to copy (https:// URL, local file path, or data: URI), or "persona" to use slot 1 of persona_id.
reference_images	array	optional	Up to 6 reference images (furniture, materials, products, mood boards) to draw from.
precision	integer	optional	How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output image format.
variations	integer	optional	Number of alternative designs (1-4, default 1); each is billed as a generation.
persona_id	integer	optional	Persona whose saved images/knowledge to use (see luw_personas).

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Photo of the building (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What you want, in plain language.",
      "type": "string",
      "maxLength": 4000
    },
    "styles": {
      "description": "Design style names, e.g. [\"Japandi\"]. Case-sensitive; see luw_list_options.",
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "building_type": {
      "description": "Building/space type, e.g. \"Modern House Exterior\", \"Luxury Villa Exterior\", \"Outdoor Patio\" (see luw_list_options kind=\"exterior_types\").",
      "type": "string"
    },
    "style_reference": {
      "description": "Style-transfer source: an image whose look to copy (https:// URL, local file path, or data: URI), or \"persona\" to use slot 1 of persona_id.",
      "type": "string"
    },
    "reference_images": {
      "description": "Up to 6 reference images (furniture, materials, products, mood boards) to draw from.",
      "maxItems": 6,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "description": "Reference image (https:// URL, local file path, or data: URI)."
      }
    },
    "precision": {
      "description": "How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    },
    "variations": {
      "description": "Number of alternative designs (1-4, default 1); each is billed as a generation.",
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    },
    "persona_id": {
      "description": "Persona whose saved images/knowledge to use (see luw_personas).",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_sketch_to_render

Turn a hand sketch, line drawing, floor-plan perspective or rough draft into a photorealistic render. Costs 1 credit per variation.

Parameters12

image	string	required	The sketch or drawing (https:// URL, local file path, or data: URI).
prompt	string	optional	What you want, in plain language.
styles	array	optional	Design style names, e.g. ["Japandi"]. Case-sensitive; see luw_list_options.
space_type	string	optional	What the sketch shows, e.g. "Living Room" or "Modern House Exterior".
style_reference	string	optional	Style-transfer source: an image whose look to copy (https:// URL, local file path, or data: URI), or "persona" to use slot 1 of persona_id.
precision	integer	optional	How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output image format.
variations	integer	optional	Number of alternative designs (1-4, default 1); each is billed as a generation.
persona_id	integer	optional	Persona whose saved images/knowledge to use (see luw_personas).

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "The sketch or drawing (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What you want, in plain language.",
      "type": "string",
      "maxLength": 4000
    },
    "styles": {
      "description": "Design style names, e.g. [\"Japandi\"]. Case-sensitive; see luw_list_options.",
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "space_type": {
      "description": "What the sketch shows, e.g. \"Living Room\" or \"Modern House Exterior\".",
      "type": "string"
    },
    "style_reference": {
      "description": "Style-transfer source: an image whose look to copy (https:// URL, local file path, or data: URI), or \"persona\" to use slot 1 of persona_id.",
      "type": "string"
    },
    "precision": {
      "description": "How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    },
    "variations": {
      "description": "Number of alternative designs (1-4, default 1); each is billed as a generation.",
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    },
    "persona_id": {
      "description": "Persona whose saved images/knowledge to use (see luw_personas).",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_render

Turn a 3D model view, CAD/BIM screenshot, clay render or basic visualization into a photorealistic architectural render. Costs 1 credit per variation.

Parameters7

image	string	required	The 3D view or base render (https:// URL, local file path, or data: URI).
prompt	string	optional	What you want, in plain language.
reference_images	array	optional	Up to 6 reference images (furniture, materials, products, mood boards) to draw from.
precision	integer	optional	How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
format	string	optional	Output image format.
variations	integer	optional	Number of alternative designs (1-4, default 1); each is billed as a generation.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "The 3D view or base render (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What you want, in plain language.",
      "type": "string",
      "maxLength": 4000
    },
    "reference_images": {
      "description": "Up to 6 reference images (furniture, materials, products, mood boards) to draw from.",
      "maxItems": 6,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "description": "Reference image (https:// URL, local file path, or data: URI)."
      }
    },
    "precision": {
      "description": "How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    },
    "variations": {
      "description": "Number of alternative designs (1-4, default 1); each is billed as a generation.",
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_edit_image

Edit any image with a plain-language instruction: "make the sofa green velvet", "add a pendant lamp over the table", "turn it into a night scene". Pass products, materials or a mood board as reference_images to place or apply them. For edits restricted to an exact area, use luw_magic_wand. Costs 1 credit per variation.

Parameters9

image	string	required	Image to edit (https:// URL, local file path, or data: URI).
prompt	string	required	The edit to make.
reference_images	array	optional	Up to 6 reference images (furniture, materials, products, mood boards) to draw from.
engine	string	optional	Model: aria (default), symphony (Symphony-3) or nano-banana-2.
resolution	string	optional	Output resolution (default 2k).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output image format.
variations	integer	optional	Number of alternative designs (1-4, default 1); each is billed as a generation.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Image to edit (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The edit to make."
    },
    "reference_images": {
      "description": "Up to 6 reference images (furniture, materials, products, mood boards) to draw from.",
      "maxItems": 6,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "description": "Reference image (https:// URL, local file path, or data: URI)."
      }
    },
    "engine": {
      "description": "Model: aria (default), symphony (Symphony-3) or nano-banana-2.",
      "type": "string",
      "enum": [
        "aria",
        "symphony",
        "nano-banana-2"
      ]
    },
    "resolution": {
      "description": "Output resolution (default 2k).",
      "type": "string",
      "enum": [
        "2k",
        "4k"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    },
    "variations": {
      "description": "Number of alternative designs (1-4, default 1); each is billed as a generation.",
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    }
  },
  "required": [
    "image",
    "prompt"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_magic_wand

Change only a masked area of an image. Give a prompt to add/replace what's there, remove=true to erase it, or material_image to re-surface it (e.g. new flooring or wall tiles). The mask is a black-and-white image the same size as the input; white marks the area to change. Get masks from luw_segment. Costs 1 credit.

Parameters10

image	string	required	Image to edit (https:// URL, local file path, or data: URI).
mask_image	string	required	Black/white mask, white = area to change (https:// URL, local file path, or data: URI).
prompt	string	optional	What to put in the masked area.
remove	boolean	optional	Remove whatever is in the masked area.
material_image	string	optional	Material/texture to apply to the masked area (https:// URL, local file path, or data: URI); luw_list_options kind="materials" has a ready-made catalog.
keep_structure	boolean	optional	Preserve the masked area's geometry/lines while changing its look (structure-guided fill).
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output image format.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Image to edit (https:// URL, local file path, or data: URI)."
    },
    "mask_image": {
      "type": "string",
      "minLength": 1,
      "description": "Black/white mask, white = area to change (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What to put in the masked area.",
      "type": "string",
      "maxLength": 4000
    },
    "remove": {
      "description": "Remove whatever is in the masked area.",
      "type": "boolean"
    },
    "material_image": {
      "description": "Material/texture to apply to the masked area (https:// URL, local file path, or data: URI); luw_list_options kind=\"materials\" has a ready-made catalog.",
      "type": "string"
    },
    "keep_structure": {
      "description": "Preserve the masked area's geometry/lines while changing its look (structure-guided fill).",
      "type": "boolean"
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    }
  },
  "required": [
    "image",
    "mask_image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_landscape_design

Design a garden, yard or outdoor area inside a masked region of a photo, with plants chosen for the location's climate and sun exposure. Costs 1 credit.

Parameters8

image	string	required	Photo of the outdoor area (https:// URL, local file path, or data: URI).
mask_image	string	required	Black/white mask, white = area to landscape (https:// URL, local file path, or data: URI).
prompt	string	optional	What you want, in plain language.
city	string	optional	Location, for climate-appropriate planting, e.g. "Antalya".
sun_exposure	string	optional	e.g. "Full sun (6+ hours)", "Partial sun (4 - 6 hours)", "Shade (less than 4 hours)".
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output image format.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Photo of the outdoor area (https:// URL, local file path, or data: URI)."
    },
    "mask_image": {
      "type": "string",
      "minLength": 1,
      "description": "Black/white mask, white = area to landscape (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What you want, in plain language.",
      "type": "string",
      "maxLength": 4000
    },
    "city": {
      "description": "Location, for climate-appropriate planting, e.g. \"Antalya\".",
      "type": "string"
    },
    "sun_exposure": {
      "description": "e.g. \"Full sun (6+ hours)\", \"Partial sun (4 - 6 hours)\", \"Shade (less than 4 hours)\".",
      "type": "string"
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    }
  },
  "required": [
    "image",
    "mask_image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_image_tools

One-step image utilities, 1 credit each: - upscale: enhance quality and enlarge 2x/4x/8x (Photo Enhance AI) - expand: outpaint a tightly cropped architectural photo to a wider view (Expand AI) - remove_furniture: empty a furnished room, keeping walls, floor and windows (Remove Furniture AI) - vectorize: convert a photo or drawing into a clean SVG vector (Vector AI)

Parameters5

operation	string	required
image	string	required	Input image (https:// URL, local file path, or data: URI).
scale	any	optional	upscale only: 2, 4 or 8 (default 2).
precision	integer	optional	How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.
format	string	optional	Output image format.

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string",
      "enum": [
        "upscale",
        "expand",
        "remove_furniture",
        "vectorize"
      ]
    },
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Input image (https:// URL, local file path, or data: URI)."
    },
    "scale": {
      "description": "upscale only: 2, 4 or 8 (default 2).",
      "anyOf": [
        {
          "type": "number",
          "const": 2
        },
        {
          "type": "number",
          "const": 4
        },
        {
          "type": "number",
          "const": 8
        }
      ]
    },
    "precision": {
      "description": "How strictly to keep the input's structure: 90 = precise, 75 = balanced, 40 = creative.",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    }
  },
  "required": [
    "operation",
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_background

Cut out a product/object from its background (transparent PNG) — or, with a prompt, place it in a new generated scene for marketing shots ("on a marble kitchen counter, morning light"). Omit prompt to just remove the background. Costs 1 credit.

Parameters5

image	string	required	Product or object photo (https:// URL, local file path, or data: URI).
prompt	string	optional	New background to generate. Leave empty to remove the background.
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
format	string	optional	Output image format.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Product or object photo (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "New background to generate. Leave empty to remove the background.",
      "type": "string",
      "maxLength": 4000
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_segment

Detect objects in a photo and return black-and-white masks as image URLs — every object (wall, floor, sofa, …) or only what you describe in prompt. Feed a mask URL into luw_magic_wand or luw_landscape_design to edit exactly that area. Costs 1 credit.

Parameters3

image	string	required	Photo to segment (https:// URL, local file path, or data: URI).
prompt	string	optional	What to segment, e.g. "walls", "the sofa", "lawn". Omit to segment everything.
labels	array	optional	Keep only masks whose label contains one of these words (e.g. ["floor", "wall"]).

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Photo to segment (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What to segment, e.g. \"walls\", \"the sofa\", \"lawn\". Omit to segment everything.",
      "type": "string",
      "maxLength": 500
    },
    "labels": {
      "description": "Keep only masks whose label contains one of these words (e.g. [\"floor\", \"wall\"]).",
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_generate_image

Generate a photorealistic image or illustration from a text prompt (optionally guided by an input image) — concept art, interiors, products, marketing visuals. Set format="svg" for a vector illustration (Fluw Vector AI). Costs 2 credits per image.

Parameters9

prompt	string	required	What to generate.
aspect_ratio	string	optional
styles	array	optional	Design style names, e.g. ["Japandi"]. Case-sensitive; see luw_list_options.
image	string	optional	Optional guide image (https:// URL, local file path, or data: URI).
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.
format	string	optional	Output format; svg switches to Fluw Vector AI.
variations	integer	optional	Number of alternative designs (1-4, default 1); each is billed as a generation.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "What to generate."
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "16:9",
        "3:2",
        "4:3",
        "1:1",
        "3:4",
        "2:3",
        "9:16"
      ]
    },
    "styles": {
      "description": "Design style names, e.g. [\"Japandi\"]. Case-sensitive; see luw_list_options.",
      "maxItems": 5,
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Optional guide image (https:// URL, local file path, or data: URI)."
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "format": {
      "description": "Output format; svg switches to Fluw Vector AI.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp",
        "svg"
      ]
    },
    "variations": {
      "description": "Number of alternative designs (1-4, default 1); each is billed as a generation.",
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    }
  },
  "required": [
    "prompt"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_generate_pattern

Generate a seamless, tileable pattern or texture — tiles, wallpaper, fabric, terrazzo, wood, stone — ready to repeat across a surface. Costs 1 credit.

Parameters6

prompt	string	required	The pattern, e.g. "blue and white Moroccan zellige tiles".
image	string	optional	Optional reference image (https:// URL, local file path, or data: URI).
size	any	optional	Output size in px. aria: 512 or 768 (default); symphony: 512 or 1024 (default).
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
format	string	optional	Output image format.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 4000,
      "description": "The pattern, e.g. \"blue and white Moroccan zellige tiles\"."
    },
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Optional reference image (https:// URL, local file path, or data: URI)."
    },
    "size": {
      "description": "Output size in px. aria: 512 or 768 (default); symphony: 512 or 1024 (default).",
      "anyOf": [
        {
          "type": "number",
          "const": 512
        },
        {
          "type": "number",
          "const": 768
        },
        {
          "type": "number",
          "const": 1024
        }
      ]
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "format": {
      "description": "Output image format.",
      "type": "string",
      "enum": [
        "jpg",
        "png",
        "webp"
      ]
    }
  },
  "required": [
    "prompt"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_generate_video

Animate a design image into a short cinematic video — fly-throughs, dolly moves, drone shots, reveals. Camera motions: A Forward Dolly, Flythrough Cinematic, Return to Empty Room, Lighting and Color Details, Drone flying to center, Dramatic Zoom Out, Reverse Zoom In, Slow Pull Back, Reveal Zoom, Ground to Sky Tilt, Side Tracking Zoom, Aerial Descent. Takes a few minutes — expect a processing_url to collect with luw_get_result. Costs 10 credits (aria) or 20 (symphony).

Parameters6

image	string	required	Start frame (a render or photo) (https:// URL, local file path, or data: URI).
prompt	string	optional	What should happen in the video.
camera_motion	string	optional	One of the camera motions listed above, e.g. "Flythrough Cinematic".
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
enhance_prompt	boolean	optional	Let Luw.ai's prompt enhancer expand a short prompt.
seed	integer	optional	Fix for reproducible results.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Start frame (a render or photo) (https:// URL, local file path, or data: URI)."
    },
    "prompt": {
      "description": "What should happen in the video.",
      "type": "string",
      "maxLength": 4000
    },
    "camera_motion": {
      "description": "One of the camera motions listed above, e.g. \"Flythrough Cinematic\".",
      "type": "string"
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "enhance_prompt": {
      "description": "Let Luw.ai's prompt enhancer expand a short prompt.",
      "type": "boolean"
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_image_to_3d

Generate a textured 3D model (GLB) from a photo of an object — furniture, decor, products. Add up to 3 photos from other angles for better accuracy. For text-to-3D, first make an image with luw_generate_image. Costs 3 credits (aria) or 8 (symphony).

Parameters7

image	string	required	Photo of the object (https:// URL, local file path, or data: URI).
extra_angles	array	optional
engine	string	optional	Luw.ai model: aria (default) or symphony (Symphony-3).
reflections	boolean	optional	Enable reflective materials (symphony engine only).
simplify	integer	optional	Mesh simplification level (0 = off, default).
texture	integer	optional	Texture size setting (0 = default).
seed	integer	optional	Fix for reproducible results.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "minLength": 1,
      "description": "Photo of the object (https:// URL, local file path, or data: URI)."
    },
    "extra_angles": {
      "maxItems": 3,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "description": "Another angle of the same object (https:// URL, local file path, or data: URI)."
      }
    },
    "engine": {
      "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      "type": "string",
      "enum": [
        "aria",
        "symphony"
      ]
    },
    "reflections": {
      "description": "Enable reflective materials (symphony engine only).",
      "type": "boolean"
    },
    "simplify": {
      "description": "Mesh simplification level (0 = off, default).",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "texture": {
      "description": "Texture size setting (0 = default).",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "seed": {
      "description": "Fix for reproducible results.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "image"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_get_result

Collect the result of a Luw.ai generation that was still processing (tools return a processing_url when a job outlasts their wait). Waits for the job to finish (up to the server's wait limit) — call again if it's still running. Free; never re-run a generation instead.

Parameters2

processing_url	string	required	The processing_url returned by a generation tool.
wait	boolean	optional	Wait for completion (default true). false = check once and return immediately.

Raw schema

{
  "type": "object",
  "properties": {
    "processing_url": {
      "type": "string",
      "minLength": 1,
      "description": "The processing_url returned by a generation tool."
    },
    "wait": {
      "description": "Wait for completion (default true). false = check once and return immediately.",
      "type": "boolean"
    }
  },
  "required": [
    "processing_url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_upload_file

Upload an image, video or 3D file to Luw.ai storage and get a URL usable by every Luw.ai tool. Rarely needed: all tools already accept local paths and data: URIs and upload them automatically. Useful to get a shareable URL, to re-host an image from a site Luw.ai can't reach, or to store a file permanently.

Parameters3

source	string	required	Local file path, file:// URL, data: URI, or an https:// URL to copy into Luw.ai storage.
persistent	boolean	optional	Keep the file in your Luw.ai storage permanently. Default: temporary, auto-deleted after 12 hours.
persona_id	integer	optional	Persona to store a persistent file under (default: your first persona).

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "minLength": 1,
      "description": "Local file path, file:// URL, data: URI, or an https:// URL to copy into Luw.ai storage."
    },
    "persistent": {
      "description": "Keep the file in your Luw.ai storage permanently. Default: temporary, auto-deleted after 12 hours.",
      "type": "boolean"
    },
    "persona_id": {
      "description": "Persona to store a persistent file under (default: your first persona).",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "source"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_list_options

Look up valid values for other Luw.ai tools: design_styles (styles param), interior_types (room_type), exterior_types (building_type), video_styles (camera_motion), materials (Magic Wand material_image catalog), professions (persona profession). Free.

Parameters3

kind	string	required
search	string	optional	Case-insensitive filter on names/descriptions.
details	boolean	optional	Include descriptions and preview image URLs (longer output).

Raw schema

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "enum": [
        "design_styles",
        "interior_types",
        "exterior_types",
        "video_styles",
        "materials",
        "professions"
      ]
    },
    "search": {
      "description": "Case-insensitive filter on names/descriptions.",
      "type": "string"
    },
    "details": {
      "description": "Include descriptions and preview image URLs (longer output).",
      "type": "boolean"
    }
  },
  "required": [
    "kind"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_run_model

Call POST /generate with raw API parameters, for models or options the dedicated tools don't cover (e.g. persona-slot inputs, webhooks). Models: interior, exterior, sketch, render, magicprompt, magicwand, moodboard, landscape, enhance, expand, vector, removefurniture, segment, segmentprompt, fluw, fluwvector, pattern, changebg, removebg, video, 3dgen. Parameter reference: https://luw-ai.gitbook.io/api. Image fields (image, mask_image, material_image, style_transfer, extra_image_1…6) also accept local paths and data: URIs. Spends credits like the model's own tool.

Parameters2

model	string	required	Model id, e.g. interior or magicprompt.
params	object	optional	Other /generate parameters, e.g. {"image": "…", "prompt": "…", "precise": 75}.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "minLength": 1,
      "description": "Model id, e.g. interior or magicprompt."
    },
    "params": {
      "description": "Other /generate parameters, e.g. {\"image\": \"…\", \"prompt\": \"…\", \"precise\": 75}.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    }
  },
  "required": [
    "model"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_archigpt

Ask Luw.ai's ArchiGPT, an AI architect: design advice, feng shui, space planning, material and color suggestions, technical questions, and estimating square meters from a photo or plan. Attach an image to discuss it. Pass earlier turns in history to continue a conversation. Costs 1 credit per ~3000 words.

Parameters5

message	string	required	Your question or message.
image	string	optional	Image to discuss (https:// URL, local file path, or data: URI).
history	array	optional	Previous messages of this conversation, oldest first.
language	string	optional	Reply language, e.g. "en" or "tr". Auto-detected when omitted.
persona_id	integer	optional	Persona that remembers this conversation.

Raw schema

{
  "type": "object",
  "properties": {
    "message": {
      "type": "string",
      "minLength": 1,
      "maxLength": 8000,
      "description": "Your question or message."
    },
    "image": {
      "description": "Image to discuss (https:// URL, local file path, or data: URI).",
      "type": "string"
    },
    "history": {
      "description": "Previous messages of this conversation, oldest first.",
      "maxItems": 50,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "assistant"
            ]
          },
          "content": {
            "type": "string"
          }
        },
        "required": [
          "role",
          "content"
        ]
      }
    },
    "language": {
      "description": "Reply language, e.g. \"en\" or \"tr\". Auto-detected when omitted.",
      "type": "string"
    },
    "persona_id": {
      "description": "Persona that remembers this conversation.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "message"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_personas

Personas hold a reusable design identity: style knowledge plus saved images (trainings). Slots 1-6 train the persona's visual style (slot 1 is the style-transfer reference used by style_reference="persona"), slot 7 is the default input image, 8+ are free-form data; add_training without a slot "likes" a design. Pass persona_id to generation tools to use one. Actions: list, get, create, update, delete, list_trainings, add_training, update_training, delete_training, clear_slot.

Parameters14

action	string	required
persona_id	integer	optional
name	string	optional
title	string	optional	Short description of the persona.
knows	string	optional	Comma-separated style knowledge, e.g. "Modern,Minimalism" or room/building types.
profession	string	optional	Tool the persona belongs to, e.g. Interior, Exterior, MagicPrompt, MagicWand, Enhance, Video, Render, 3DGen, Fluw, Sketch, Landscape, MoodBoard, ArchiGPT. For list: only that tool's personas (fast).
search	string	optional	list: filter by name/title/knows.
page	integer	optional	list / list_trainings: page number (default 1).
limit	integer	optional	list / list_trainings: items per page (default 20).
training_id	integer	optional
image	string	optional	Training image (https:// URL, local file path, or data: URI); stored permanently.
slot	integer	optional
info	string	optional	Description of the training image.
extras	string	optional	Extra metadata, e.g. the prompt behind a liked design.

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "get",
        "create",
        "update",
        "delete",
        "list_trainings",
        "add_training",
        "update_training",
        "delete_training",
        "clear_slot"
      ]
    },
    "persona_id": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "name": {
      "type": "string"
    },
    "title": {
      "description": "Short description of the persona.",
      "type": "string"
    },
    "knows": {
      "description": "Comma-separated style knowledge, e.g. \"Modern,Minimalism\" or room/building types.",
      "type": "string"
    },
    "profession": {
      "description": "Tool the persona belongs to, e.g. Interior, Exterior, MagicPrompt, MagicWand, Enhance, Video, Render, 3DGen, Fluw, Sketch, Landscape, MoodBoard, ArchiGPT. For list: only that tool's personas (fast).",
      "type": "string"
    },
    "search": {
      "description": "list: filter by name/title/knows.",
      "type": "string"
    },
    "page": {
      "description": "list / list_trainings: page number (default 1).",
      "type": "integer",
      "minimum": 1,
      "maximum": 9007199254740991
    },
    "limit": {
      "description": "list / list_trainings: items per page (default 20).",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "training_id": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "image": {
      "description": "Training image (https:// URL, local file path, or data: URI); stored permanently.",
      "type": "string"
    },
    "slot": {
      "type": "integer",
      "minimum": 1,
      "maximum": 9007199254740991
    },
    "info": {
      "description": "Description of the training image.",
      "type": "string"
    },
    "extras": {
      "description": "Extra metadata, e.g. the prompt behind a liked design.",
      "type": "string"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

luw_projects

Organize work in Luw.ai projects (called boards in the API), with nested folders and media. Use add_media to save generated results into a project. Actions: list, get, create, rename, delete, list_folders, create_folder, update_folder, delete_folder, add_media, delete_media, move_media.

Parameters9

action	string	required
project_id	integer	optional
name	string	optional	Project or folder name.
folder_id	integer	optional	Folder to act on, or target folder for add_media/move_media (omit = project root).
parent_id	integer	optional	Parent folder for nested folders.
media_id	integer	optional
url	string	optional	add_media: the media (https:// URL, local file path, or data: URI).
control_image	string	optional	add_media: optional source/reference image, e.g. the original photo of a redesign.
extras	string	optional	add_media: metadata as a JSON string, e.g. {"prompt": "…"}.

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "get",
        "create",
        "rename",
        "delete",
        "list_folders",
        "create_folder",
        "update_folder",
        "delete_folder",
        "add_media",
        "delete_media",
        "move_media"
      ]
    },
    "project_id": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "name": {
      "description": "Project or folder name.",
      "type": "string"
    },
    "folder_id": {
      "description": "Folder to act on, or target folder for add_media/move_media (omit = project root).",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "parent_id": {
      "description": "Parent folder for nested folders.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "media_id": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    },
    "url": {
      "description": "add_media: the media (https:// URL, local file path, or data: URI).",
      "type": "string"
    },
    "control_image": {
      "description": "add_media: optional source/reference image, e.g. the original photo of a redesign.",
      "type": "string"
    },
    "extras": {
      "description": "add_media: metadata as a JSON string, e.g. {\"prompt\": \"…\"}.",
      "type": "string"
    }
  },
  "required": [
    "action"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md12 KBView on GitHub

Official Luw.ai MCP server

AI interior, exterior and landscape design, photoreal rendering, image editing, video and 3D,
inside Claude, Cursor, VS Code, Windsurf, Codex and any other MCP client.

text

You:     Redesign ~/Desktop/living-room.jpg in Japandi style, give me 2 options.
Claude:  ⟶ luw_interior_design  ✓ 2 designs in 21s   [shows both images]
You:     Love the first one. Make the sofa green velvet, then turn it into a fly-through video.
Claude:  ⟶ luw_edit_image ⟶ luw_generate_video   ✓

Quick start

1. Get an API key at app.luw.ai/dashboard/api. New accounts get free credits.

2. Add Luw.ai to your client. Pick one:

Claude Code

bash

claude mcp add luw --scope user --env LUW_API_KEY=YOUR_LUW_API_KEY -- npx -y @luw-ai/mcp

No-install alternative (hosted server):

bash

claude mcp add --transport http luw https://mcp.luw.ai/mcp --header "Authorization: Bearer YOUR_LUW_API_KEY"

Claude Desktop

One click: download luw.mcpb, double-click it, paste your API key. Nothing else to install.

Or add this to claude_desktop_config.json (Settings → Developer → Edit Config):

json

{
  "mcpServers": {
    "luw": {
      "command": "npx",
      "args": ["-y", "@luw-ai/mcp"],
      "env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
    }
  }
}

Cursor

Click Add to Cursor above and replace YOUR_LUW_API_KEY, or add to ~/.cursor/mcp.json:

json

{
  "mcpServers": {
    "luw": {
      "command": "npx",
      "args": ["-y", "@luw-ai/mcp"],
      "env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
    }
  }
}

VS Code (Copilot)

Click Install in VS Code above. VS Code asks for your key and keeps it in its secret storage. Or add to .vscode/mcp.json:

json

{
  "inputs": [{ "type": "promptString", "id": "luw_api_key", "description": "Luw.ai API key", "password": true }],
  "servers": {
    "luw": {
      "command": "npx",
      "args": ["-y", "@luw-ai/mcp"],
      "env": { "LUW_API_KEY": "${input:luw_api_key}" }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json

{
  "mcpServers": {
    "luw": {
      "command": "npx",
      "args": ["-y", "@luw-ai/mcp"],
      "env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
    }
  }
}

OpenAI Codex CLI

bash

codex mcp add luw --env LUW_API_KEY=YOUR_LUW_API_KEY -- npx -y @luw-ai/mcp

Or in ~/.codex/config.toml:

toml

[mcp_servers.luw]
command = "npx"
args = ["-y", "@luw-ai/mcp"]
env = { LUW_API_KEY = "YOUR_LUW_API_KEY" }

Gemini CLI

Add to ~/.gemini/settings.json:

json

{
  "mcpServers": {
    "luw": {
      "command": "npx",
      "args": ["-y", "@luw-ai/mcp"],
      "env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
    }
  }
}

Any client with remote MCP support (hosted, nothing to install)


URL	`https://mcp.luw.ai/mcp`
Transport	Streamable HTTP
Auth header	`Authorization: Bearer YOUR_LUW_API_KEY`

json

{
  "mcpServers": {
    "luw": {
      "url": "https://mcp.luw.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_LUW_API_KEY" }
    }
  }
}

If your client only accepts a URL and can't send headers (for example ChatGPT connectors), use https://mcp.luw.ai/mcp?api_key=YOUR_LUW_API_KEY. Anyone who has that URL can spend your credits, so keep it private.

The hosted server is stateless and stores nothing. Your key goes straight to the Luw.ai API on each request. It can't read files from your computer, so pass image URLs, or use the local npx setup to work with local files.

Windows: if npx isn't found, use "command": "cmd", "args": ["/c", "npx", "-y", "@luw-ai/mcp"]. Requires Node.js 18 or later. The Claude Desktop extension bundles everything it needs.

What you can ask

"Redesign this bedroom (~/Downloads/bedroom.jpg) as Mid-Century Modern, 3 variations."
"This listing photo is an empty room. Stage it as a cozy Scandinavian living room."
"Render my sketch plan-sketch.png as a photoreal modern villa at golden hour."
"Change the floor in this kitchen to herringbone oak." (segments the floor, then swaps the material)
"Remove all the furniture from this room."
"Put this chair photo on a terrazzo floor in a sunlit gallery for an ad."
"Turn this render into a drone fly-through video."
"Make a 3D model of this armchair from these 3 photos."
"Seamless blue zellige tile texture, 1024px."
"Ask ArchiGPT how to improve the feng shui of this floor plan."

Built-in prompts show up as slash commands or prompt templates in your client: redesign_room, stage_empty_room, sketch_to_render, product_shot.

Tools

Tool	What it does	Credits
`luw_interior_design`	Redesign a room in any style; `empty_room` for virtual staging	1
`luw_exterior_design`	Redesign a facade or building exterior	1
`luw_sketch_to_render`	Sketch or drawing to photoreal render	1
`luw_render`	3D, CAD or clay view to photoreal render	1
`luw_edit_image`	Edit any image with a sentence (Magic Prompt); 2K/4K	1
`luw_magic_wand`	Masked edit: replace, remove, or apply a material	1
`luw_landscape_design`	Gardens and outdoor areas, matched to climate and sun	1
`luw_image_tools`	`upscale` 2/4/8×, `expand`, `remove_furniture`, `vectorize` to SVG	1
`luw_background`	Remove a background, or replace it with a generated scene	1
`luw_segment`	Object masks (all objects, or by prompt) as image URLs	1
`luw_generate_image`	Text to image (Fluw), or `format: "svg"` for vectors	2
`luw_generate_pattern`	Seamless, tileable textures and patterns	1
`luw_generate_video`	Image to cinematic video with 12 camera motions	10 (20 with Symphony)
`luw_image_to_3d`	Photos to a textured 3D model (GLB)	3 (8 with Symphony)
`luw_archigpt`	Chat with ArchiGPT, an AI architect (accepts images)	1 per ~3k words
`luw_get_result`	Collect a long-running job (free)	0
`luw_list_options`	Valid styles, room and building types, camera motions, materials (free)	0
`luw_upload_file`	Upload a file to Luw.ai storage and get a URL (free)	0
`luw_run_model`	Call any Luw.ai model with raw API parameters	varies
`luw_personas`	Personas: reusable style identity, training images and slots	0
`luw_projects`	Projects (boards), folders and media	0
`luw_team`	Enterprise: credits, usage, members, invitations (opt-in)	0

Every generation uses your Luw.ai credits. Variations are billed one generation each.

How it works

Local files just work. Any image argument accepts an https:// URL, a local path (~/Desktop/room.jpg), or a data: URI. Local files are uploaded to Luw.ai storage as temporary files (deleted after 12 hours) and cached for the session, so repeated edits don't upload the same file again.
You see the results. Finished images are embedded in the tool result, so Claude and other clients show them inline. Set LUW_OUTPUT_DIR to also save every result to disk.
Long jobs don't time out. A call waits up to 50 seconds and streams progress to clients that show it. If a job like a video takes longer, the tool returns a processing_url and the assistant collects it with luw_get_result, without generating (or paying) twice.
Never billed twice. Every generation request carries an Idempotency-Key, so if a network error forces a retry, Luw.ai returns the original job instead of charging again.
Masks are handled for you. luw_segment returns masks as URLs, so "change the floor" becomes segment ⟶ magic wand with no manual masking.
Fast startup. The package is one bundled file with zero dependencies, so npx downloads a single ~260 KB package and starts right away.

Configuration

Variable	Default
`LUW_API_KEY`	(required)	Your API key (get one). `LUW_API_TOKEN` also works.
`LUW_OUTPUT_DIR`	(off)	Also download results (images, videos, GLB, SVG) into this folder
`LUW_TOOLSETS`	all except `team`	Comma-separated list from `generate`, `archigpt`, `personas`, `projects`, `team`, or `all`
`LUW_WAIT_TIMEOUT_SECONDS`	`50`	How long a call waits before returning a `processing_url`. Raise it for clients with long tool timeouts, such as Claude Code.
`LUW_INLINE_IMAGES`	`true`	Embed result images in tool output
`LUW_API_BASE_URL`	`https://api.luw.ai/v2`	API endpoint override

Self-hosting the remote server

The same package serves the hosted Streamable HTTP endpoint:

bash

npx -y @luw-ai/mcp --http --port 8080 --host 0.0.0.0   # MCP at /mcp, health at /health

bash

docker build -t luw-mcp . && docker run -p 8080:8080 luw-mcp

It's stateless and holds no secrets. Each request brings its own key in Authorization: Bearer …, X-Luw-Api-Key, or ?api_key=. It deploys to Vercel as-is (vercel.json is included), and a Procfile is included for Heroku. See docs/maintainers.md for deployment and release steps.

Development

bash

npm ci
npm test               # unit and protocol tests (no network)
npm run build          # bundles dist/cli.js
npm run inspector      # try every tool in the MCP Inspector
LUW_API_KEY=... npm run smoke            # live checks against the real API (free)
LUW_API_KEY=... npm run smoke -- --paid  # plus one real generation (1 credit)
npm run mcpb           # build/luw.mcpb, the Claude Desktop extension

Support

API reference: luw-ai.gitbook.io/api
Issues: GitHub Issues
Email: support@luvi.io

Install

Tools (21)

luw_interior_designluw_exterior_designluw_sketch_to_renderluw_renderluw_edit_imageluw_magic_wandluw_landscape_designluw_image_tools

Configuration

Environment variables

LUW_API_KEYrequiredsecret

Your Luw.ai API key from https://app.luw.ai/dashboard/api

LUW_OUTPUT_DIR

Optional folder where generated files are also downloaded

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@luw-ai/mcp@0.2.0"
      ],
      "env": {
        "LUW_API_KEY": "<YOUR_LUW_API_KEY>",
        "LUW_OUTPUT_DIR": "<YOUR_LUW_OUTPUT_DIR>"
      }
    }
  }
}

ai.luw/mcp Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

luw_interior_design

luw_exterior_design

luw_sketch_to_render

luw_render

luw_edit_image

luw_magic_wand

luw_landscape_design

luw_image_tools

luw_background

luw_segment

luw_generate_image

luw_generate_pattern

luw_generate_video

luw_image_to_3d

luw_get_result

luw_upload_file

luw_list_options

luw_run_model

luw_archigpt

luw_personas

luw_projects

Official Luw.ai MCP server

Quick start

What you can ask

Tools

How it works

Configuration

Self-hosting the remote server

Development

Support

Install

Configuration

Related servers