Luw.ai

ai.luwv0.1.0Updated Oct 7, 2026

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

VerifiedStreamable HTTPWeb executableAI & MLMedia & Design

Overview

AI-generated overview

Lets an assistant generate and edit interior, exterior and landscape designs, photoreal renders, images, video and 3D models through Luw.ai.

What it does
Luw.ai exposes tools for room and facade redesign, virtual staging of empty rooms, sketch-to-render, image editing with a sentence, masked edits, background removal, upscaling, segmentation, seamless pattern generation, text-to-image, image-to-video and image-to-3D. It also offers an AI architect chat, plus free helpers for listing options, uploading files, collecting long-running jobs and managing personas and projects. Results are returned inline as images, and long jobs return a processing URL that the assistant collects later.
When to use it
Use it when you want design or rendering work done from inside an MCP client: restyling a room photo, staging a listing, turning a sketch or 3D view into a photoreal render, editing product shots, or producing short videos and 3D models from images.
Requirements
A Luw.ai API key, supplied as the LUW_API_KEY environment variable for the local npm package or as an Authorization Bearer header for the hosted endpoint. The local package needs Node.js 18 or later; the hosted server needs no install. Optional settings include LUW_OUTPUT_DIR, LUW_TOOLSETS, LUW_WAIT_TIMEOUT_SECONDS, LUW_INLINE_IMAGES and LUW_API_BASE_URL.
Before you install
Every generation spends Luw.ai credits, and variations are billed individually; video and 3D cost more. The API key is a secret, and a URL carrying it in a query parameter can be used by anyone who has it. Local files passed to the tools are uploaded to Luw.ai storage as temporary files. The hosted server cannot read local files, so use image URLs or the local setup.

Installation

In SourceWeft

  1. Open Luw.ai in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.luw.ai/mcp"
    }
  }
}

README

[Luw.ai]

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.

[npm] [CI] [MIT]

[Add to Cursor]   [Install in VS Code]   [Add to Claude Desktop]

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)
URLhttps://mcp.luw.ai/mcp
TransportStreamable HTTP
Auth headerAuthorization: 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

ToolWhat it doesCredits
luw_interior_designRedesign a room in any style; empty_room for virtual staging1
luw_exterior_designRedesign a facade or building exterior1
luw_sketch_to_renderSketch or drawing to photoreal render1
luw_render3D, CAD or clay view to photoreal render1
luw_edit_imageEdit any image with a sentence (Magic Prompt); 2K/4K1
luw_magic_wandMasked edit: replace, remove, or apply a material1
luw_landscape_designGardens and outdoor areas, matched to climate and sun1
luw_image_toolsupscale 2/4/8×, expand, remove_furniture, vectorize to SVG1
luw_backgroundRemove a background, or replace it with a generated scene1
luw_segmentObject masks (all objects, or by prompt) as image URLs1
luw_generate_imageText to image (Fluw), or format: "svg" for vectors2
luw_generate_patternSeamless, tileable textures and patterns1
luw_generate_videoImage to cinematic video with 12 camera motions10 (20 with Symphony)
luw_image_to_3dPhotos to a textured 3D model (GLB)3 (8 with Symphony)
luw_archigptChat with ArchiGPT, an AI architect (accepts images)1 per ~3k words
luw_get_resultCollect a long-running job (free)0
luw_list_optionsValid styles, room and building types, camera motions, materials (free)0
luw_upload_fileUpload a file to Luw.ai storage and get a URL (free)0
luw_run_modelCall any Luw.ai model with raw API parametersvaries
luw_personasPersonas: reusable style identity, training images and slots0
luw_projectsProjects (boards), folders and media0
luw_teamEnterprise: 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

VariableDefault
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_TOOLSETSall except teamComma-separated list from generate, archigpt, personas, projects, team, or all
LUW_WAIT_TIMEOUT_SECONDS50How long a call waits before returning a processing_url. Raise it for clients with long tool timeouts, such as Claude Code.
LUW_INLINE_IMAGEStrueEmbed result images in tool output
LUW_API_BASE_URLhttps://api.luw.ai/v2API 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 cinpm test               # unit and protocol tests (no network)npm run build          # bundles dist/cli.jsnpm run inspector      # try every tool in the MCP InspectorLUW_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

MIT © Luvi Technologies, Inc.

Source: README.md at commit 4b53217

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 7, 2026