AI HomeDesign is a remote MCP server that gives an AI agent 20 tools, among them change_ceiling, change_floor, change_wall. It answers at https://mcp.aihomedesign.com/{connector_token}/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
MCP server to virtually stage, redesign, enhance and declutter real-estate photos.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
change_ceiling | Change the ceiling finish in a room photo (AI applies a tasteful default). Detect `space` from the image. Provide image_url OR image_base64. Inputs: image_url, space, image_base64, wait, project_id |
change_floor | Change the floor material in a room photo (AI applies a tasteful default material). Detect `space` from the image. Provide image_url OR image_base64. Inputs: image_url, space, image_base64, wait, project_id |
change_wall | Change the wall finish/colour in a room photo (AI applies a tasteful default finish). Detect `space` (room type) from the image. Provide image_url OR image_base64. Inputs: image_url, space, image_base64, wait, project_id |
create_order | Upload one or more images and create an order. Provide `image_urls` (public URLs) and/or `image_base64` (raw base64 or data: URLs) — you can use either. Returns `order_id` and an `assets` list whose `id`s you map to a tool's input slot when Inputs: image_urls, image_base64, project_id, asset_roles |
create_project | Create a project (a container that groups all work for one property). Returns the new project's `id`. Inputs: address |
day_to_dusk | Convert a daytime EXTERIOR photo into a dusk / twilight scene. No style needed. Provide image_url OR image_base64. sky_style: leave empty to use the default sky (recommended — the 30+ named sky slugs are not publicly listed). options (multi Inputs: image_url, sky_style, options, image_base64, wait, project_id |
describe_tool | Show the input slots, widgets and selectable options for one tool, plus a ready-to-use example payload for `run_process`. Use this before `run_process` when you need the exact widget/item slugs for a tool. Inputs: tool_slug |
enhance_image | Enhance a photo: better lighting, sharpness and colour balance. No style needed. Provide image_url OR image_base64. area: indoor | outdoor (detect from the image). options (multi, optional): add-fire-to-fireplace, add-screen-to-tv. Inputs: image_url, area, options, image_base64, wait, project_id |
get_order | Fetch an order, including its input assets and any processes run on it. Inputs: order_id |
get_process | Fetch a process: its `status` (pending/processing/done/failed) and, when done, the `final_assets` with downloadable result image URLs. If a webhook result has already arrived for this process, it is returned immediately. Inputs: process_id |
get_project | Fetch a single project by id. Inputs: project_id |
interior_design | Fully redesign a FURNISHED room (walls, floors, furniture, decor) in a style. Same workflow as virtual_staging: never pick the style yourself — ask the user; detect the room type from the image. Provide image_url OR image_base64. Inputs: image_url, style, space, image_base64, wait, project_id |
list_capabilities | List every AI HomeDesign tool this MCP can run, grouped by category. Returns each tool's slug, display name, description and whether it needs one or two input images. Start here to discover what is available. |
list_projects | List your projects (paginated). Optional free-text `search` on address. Inputs: page, limit, search |
list_styles | List the allowed design styles, room types and widget options. With no argument, returns the global style/room/area lists. With a tool_slug, returns that tool's widgets and their allowed values. The staging/design helpers ONLY accept these Inputs: tool_slug |
remove_items | Auto-detect and remove furniture/clutter from a room photo (decluttering), leaving a clean empty space. No style needed. Provide image_url OR image_base64. Inputs: image_url, image_base64, wait, project_id |
run_process | Start an AI job on an existing order (full control over every tool). `asset_map` maps each of the tool's input-slot keys to an asset id from the order. `widgets` is the raw list of {slug, item_slugs}. Use `describe_tool` to get the exact sl Inputs: order_id, tool, asset_map, widgets, process_group_id |
virtual_restaging | Replace the furniture in an ALREADY-FURNISHED room with a new design style. Same workflow as virtual_staging: ask the user for the style, detect the room type from the image. Provide image_url OR image_base64. Inputs: image_url, style, space, image_base64, wait, project_id |
virtual_staging | Furnish an EMPTY room photo with AI furniture in a chosen design style. Provide the photo as `image_url` OR `image_base64` (raw base64 or a data: URL). WORKFLOW — follow exactly: • Do NOT choose a `style` yourself. Call this first with styl Inputs: image_url, style, space, image_base64, wait, project_id |
wait_for_result | Poll a process until it is `done` or `failed` (or until timeout), then return the final result image URLs. Respects the API's 5s minimum poll interval. Inputs: process_id, timeout_seconds, poll_seconds |
Every block below points at https://mcp.aihomedesign.com/{connector_token}/mcp. Pick your client and copy.
claude mcp add --transport http ai-homedesign https://mcp.aihomedesign.com/{connector_token}/mcp{
"mcpServers": {
"ai-homedesign": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.aihomedesign.com/{connector_token}/mcp"]
}
}
}{
"mcpServers": {
"ai-homedesign": {
"url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}{
"servers": {
"ai-homedesign": {
"type": "http",
"url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}{
"context_servers": {
"ai-homedesign": {
"url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}{
"mcpServers": {
"ai-homedesign": {
"serverUrl": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}{
"mcpServers": {
"ai-homedesign": {
"url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}name: AI HomeDesign
version: 0.0.1
schema: v1
mcpServers:
- name: AI HomeDesign
type: streamable-http
url: https://mcp.aihomedesign.com/{connector_token}/mcp{
"mcpServers": {
"ai-homedesign": {
"httpUrl": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}{
"mcpServers": {
"ai-homedesign": {
"type": "http",
"url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}{
"mcpServers": {
"ai-homedesign": {
"url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.aihomedesign.com%2F%7Bconnector_token%7D%2Fmcp&type=streamable_http&id=ai-homedesign&name=AI%20HomeDesign
It answered our last check on 17 October 2026 in 78 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by aihomedesign.com and served from mcp.aihomedesign.com, the vendor's own domain: https://mcp.aihomedesign.com/{connector_token}/mcp.
20, as returned by the server's own tools/list on 9 September 2026: change_ceiling, change_floor, change_wall, create_order, create_project, day_to_dusk, describe_tool, enhance_image, and 12 more.
It answered our last check on 17 October 2026 in 78 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.aihomedesign.com/{connector_token}/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.aihomedesign. Endpoint host: mcp.aihomedesign.com. ARD identifier: urn:air:com.aihomedesign:mcp:aihomedesign-mcp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.