Luw.ai
MCP serverMediaAI interior, exterior and landscape design, photoreal rendering, image editing, video and 3D.
Use Luw.ai in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Luw.ai and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the luw interior design tool from Luw.ai
No other account needed.
Details
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Install Luw.ai
The server’s own address, for the clients that take one directly. Or connect ahel once and every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user luw-ai 'https://mcp.luw.ai/mcp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://mcp.luw.ai/mcpAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=luw-ai&config=eyJ1cmwiOiJodHRwczovL21jcC5sdXcuYWkvbWNwIn0=Open the link and Cursor adds the server at that address.
ChatGPT
https://mcp.luw.ai/mcpIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add luw-ai --url 'https://mcp.luw.ai/mcp'Run it once, then sign in with codex mcp login luw-ai if the server asks for an account.
From the project's README
As published by luvi-io/luw-mcp in README.md.
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 mcp add luw --scope user --env LUW_API_KEY=YOUR_LUW_API_KEY -- npx -y @luw-ai/mcp
No-install alternative (hosted server):
claude mcp add --transport http luw https://mcp.luw.ai/mcp --header "Authorization: Bearer YOUR_LUW_API_KEY"
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):
{
"mcpServers": {
"luw": {
"command": "npx",
"args": ["-y", "@luw-ai/mcp"],
"env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
}
}
}
Click Add to Cursor above and replace YOUR_LUW_API_KEY, or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"luw": {
"command": "npx",
"args": ["-y", "@luw-ai/mcp"],
"env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
}
}
}
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:
{
"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}" }
}
}
}
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"luw": {
"command": "npx",
"args": ["-y", "@luw-ai/mcp"],
"env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
}
}
}
codex mcp add luw --env LUW_API_KEY=YOUR_LUW_API_KEY -- npx -y @luw-ai/mcp
Or in ~/.codex/config.toml:
[mcp_servers.luw]
command = "npx"
args = ["-y", "@luw-ai/mcp"]
env = { LUW_API_KEY = "YOUR_LUW_API_KEY" }
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"luw": {
"command": "npx",
"args": ["-y", "@luw-ai/mcp"],
"env": { "LUW_API_KEY": "YOUR_LUW_API_KEY" }
}
}
}
| URL | https://mcp.luw.ai/mcp |
| Transport | Streamable HTTP |
| Auth header | Authorization: Bearer YOUR_LUW_API_KEY |
{
"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.pngas 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 adata: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_DIRto 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_urland the assistant collects it withluw_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_segmentreturns 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
npxdownloads 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:
npx -y @luw-ai/mcp --http --port 8080 --host 0.0.0.0 # MCP at /mcp, health at /health
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
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
MIT © Luvi Technologies, Inc.
Tools it offers (21)
What this server listed when ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.
luw_interior_designluw_exterior_designluw_sketch_to_renderluw_renderluw_edit_imageluw_magic_wandluw_landscape_designluw_image_toolsluw_backgroundluw_segmentluw_generate_imageluw_generate_patternluw_generate_videoluw_image_to_3dluw_get_resultluw_upload_fileluw_list_optionsluw_run_modelluw_archigptluw_personasluw_projects
Signals
- Last commit
- Oct 2026
Advanced
- Delivery
- Luw.ai MCP server → your ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
ai-luw-mcp- Source
- github.com/luvi-io/luw-mcp
- Hosted endpoint
https://mcp.luw.ai/mcp