AI HomeDesign MCP

Name: AI HomeDesign MCP
Author: AIHomeDesign

作者：AIHomeDesign版本 1.0.0i★ –i在云端运行

注册名称com.aihomedesign/aihomedesign-mcp

安装

概览

作者提供的说明（英文原文）

MCP server to virtually stage, redesign, enhance and declutter real-estate photos.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在云端运行
传输方式: Streamable HTTP
分类: 设计、图片与音频

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
注册中心没有列出需要填写的密钥。

你需要

在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

打开 Settings → Connectors
点击 Add custom connector
粘贴下面的地址，然后点击 Add
如果要求登录，请登录作者的服务

https://mcp.aihomedesign.com/{connector_token}/mcp

地址中有只有你知道的 {…} 部分（例如你的账户），请复制后自行填写。

在终端中运行这条命令

claude mcp add --transport http aihomedesign 'https://mcp.aihomedesign.com/{connector_token}/mcp'

地址中有只有你知道的 {…} 部分（例如你的账户），请复制后自行填写。

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "aihomedesign": {
      "url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

地址中有只有你知道的 {…} 部分（例如你的账户），请复制后自行填写。

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "aihomedesign": {
      "type": "http",
      "url": "https://mcp.aihomedesign.com/{connector_token}/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

打开网页版 ChatGPT → Settings → Connectors (Apps)
点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
粘贴下面的地址，起个名字，然后保存
如果要求登录，请登录作者的服务

https://mcp.aihomedesign.com/{connector_token}/mcp

地址中有只有你知道的 {…} 部分（例如你的账户），请复制后自行填写。

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表；我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

✓ 通过
作者与仓库一致
注册名称已通过域名 aihomedesign.com 验证（注册中心会核实域名所有权）
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
这个地址需要填入你自己的账户信息，所以我们无法替你检查
– 不适用
使用 OAuth 登录
这个地址需要填入你自己的账户信息，所以我们无法替你检查
… 尚未检查
工具描述中没有隐藏指令
尚未检查；我们会在检查端点时读取工具列表

与“设计、图片与音频”中的其他服务器比较i

星标数多于此分类中其他 2761 个服务器的 0%
发布到注册中心的时间比此分类中其他 2761 个服务器的 15% 更新
基础检查结果等于或优于此分类中其他 2761 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

AI HomeDesign MCP 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（1.0.0）于4个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Figma Context MCP, Claude Real Video, Figma MCP Server

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Figma Context MCP

作者：GLips

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

在你的电脑上运行★ 16,165MIT5个月前更新

安装

Claude Real Video

作者：HUANGCHIHHUNGLeo

Let any LLM watch a video locally — and search everything it has ever watched.

在你的电脑上运行★ 2,284MIT2个月前更新

安装

Figma MCP Server

作者：figma

The Figma MCP server brings Figma design context directly into your AI workflow.

在云端运行★ 2,15213个月前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

AI HomeDesign MCP Server — AI Virtual Staging, Home Staging & Interior Design for Claude

An open‑source Model Context Protocol (MCP) server for AI virtual staging

and real‑estate photography editing. It turns the

AI HomeDesign photo API into natural‑language

tools, so Claude — or any MCP client — can do virtual home staging,

AI interior design, photo enhancement, decluttering, and day‑to‑dusk

conversions just by being asked.

What is this?

AI HomeDesign MCP Server exposes the AI HomeDesign V3 API as a set of Model Context Protocol tools over streamable HTTP. Any MCP‑compatible AI client — Claude Desktop, Claude in the browser, Cursor, and more — can then run professional real‑estate photo editing in plain English:

🛋️ Virtual staging — furnish an empty room with photorealistic AI furniture in a chosen design style. Digital home staging in seconds, with no physical furniture.
🎨 Virtual restaging & AI interior design — replace existing furniture or fully redesign a furnished room.
✨ Image enhancement — fix lighting, sharpness, and color balance for listing‑ready photos.
🧹 Item removal / decluttering — automatically remove furniture and clutter to reveal a clean space.
🌆 Day to dusk — convert a daytime exterior into a warm twilight / dusk scene.
🧱 Wall, floor & ceiling changes — restyle surfaces with a tasteful AI finish.

Because it speaks MCP, there is no SDK to learn — you describe what you want and the model calls the right tool with the right parameters.

Why virtual staging and home staging over MCP?

Traditional home staging means renting furniture and scheduling a shoot. Virtual staging for realtors replaces that with an edited photo — but it still costs hours in editing tools or days of turnaround from a staging service.

This server collapses that into a conversation: drop in a listing photo, pick a style, and get back a downloadable, market‑ready image. It's multi‑tenant (every caller uses their own AI HomeDesign key), stateless, and self‑hostable, so it fits both a single agent and a production PropTech product.

Available tools

Tool	What it does	Input
`list_capabilities`	List every tool, grouped by category	—
`list_styles`	List allowed design styles, room types & widget options	—
`describe_tool`	Show a tool's inputs + a ready‑to‑use example payload	tool slug
`virtual_staging`	Furnish an empty room in a design style	image + style + room
`virtual_restaging`	Swap furniture in an already‑furnished room	image + style + room
`interior_design`	Fully redesign a furnished room	image + style + room
`enhance_image`	Improve lighting, sharpness & color	image
`remove_items`	Declutter / remove furniture	image
`day_to_dusk`	Turn a daytime exterior into dusk	image
`change_wall` / `change_floor` / `change_ceiling`	Restyle a surface	image + room
`create_project` · `create_order` · `run_process` · `get_process` · `wait_for_result`	Low‑level primitives for full control	see `describe_tool`

Every helper accepts an image URL or a base64 image, and returns downloadable result‑image URLs.

Supported design styles: prime, modern, farmhouse, scandinavian, hampton, industrial, traditional, contemporary. Supported room types: bedroom, living‑room, kitchen, bathroom, dining‑room, home‑office, outdoor, nursery.

Quick start

Option A — Connect to the hosted server (no setup)

Get your API key. Sign in at aihomedesign.com, open API / Developer settings, and copy your x-api-key.
Generate your connector link. Paste that key into the generator at [aihomedesign.com/mcp](https://aihomedesign.com/mcp). The key is validated server‑side once, then stored encrypted; you get back a personal endpoint:

   https://mcp.aihomedesign.com/aihd_<your-token>/mcp

Your raw key never appears in the URL.

Add it to your AI assistant. In Claude: Settings → Connectors → Add custom connector, name it *AI HomeDesign*, and paste the URL. Every tool shows up automatically. Works with any MCP‑compatible client.

⚠️ The connector link does not contain your raw key, but it **grants access to your

account — treat it like a password.** Rotating your key in the AI HomeDesign

dashboard revokes every link previously issued for it.

Server health check, no key needed: mcp.aihomedesign.com/health

Option B — Self‑host with Docker

git clone https://github.com/AIHomeDesign/aihomedesign-mcp.git

cd aihomedesign-mcp cp .env.example .env # add your AIHD_API_KEY (and DB_DSN/TOKEN_SECRET for multi-tenant)

docker build -t aihomedesign-mcp . docker run -p 8080:8080 --env-file .env aihomedesign-mcp

The MCP endpoint is served at http://localhost:8080/mcp (streamable HTTP), with a health check at GET /health.

Option C — Run locally with Python

pip install -r requirements.txt

export AIHD_API_KEY=your_key_here python app/server.py

Configuration

All configuration is via environment variables — see .env.example.

Variable	Purpose	Default
`AIHD_API_KEY`	Default/fallback AI HomeDesign x‑api‑key	—
`AIHD_API_BASE`	API base URL	`https://api.aihomedesign.com/v3`
`PORT`	Listen port	`8080`
`DB_DSN`	Postgres DSN for token map + usage log (optional)	—
`TOKEN_SECRET`	Fernet key to encrypt user keys at rest (optional)	—
`MCP_CONNECTOR_BASE`	Base used to build connector links	—
`UPLOAD_DIR` / `PUBLIC_BASE`	Enable the built‑in image‑upload endpoint	—

Security & multi‑tenant design

Bring‑your‑own‑key: each request carries the caller's own AI HomeDesign key; jobs run under that key.
Keys never sit in the URL: the landing page validates a key, then mints an opaque aihd_… connector token; the raw key is stored encrypted at rest (Fernet) and swapped back in per request.
Usage logging records the tool, status, and timing per call — never the raw key (only a short, non‑reversible fingerprint).
Graceful degradation: if the database is unreachable, the server keeps serving.

How it works

MCP client (Claude, Cursor, …)

│ streamable HTTP /mcp ▼ AI HomeDesign MCP server ──► AI HomeDesign V3 API ──► result image URLs (this repo) (api.aihomedesign.com)

The server is built on FastMCP and Starlette/uvicorn, with a pure‑ASGI auth middleware that binds the per‑request key.

Tech stack

Python 3.12 · MCP (FastMCP) · Starlette · uvicorn · httpx · PostgreSQL (optional) · Docker.

FAQ

What is an MCP server?

An MCP server exposes tools, data, and prompts to an AI model through the Model Context Protocol — an open standard introduced by Anthropic. The model discovers the available tools at runtime and calls them itself, so you never write glue code against a bespoke SDK. This repo is an MCP server whose tools happen to edit real‑estate photos.

How do you virtually stage a photo with this?

Connect the server to Claude, then send an empty‑room photo and ask for a style — for example *"stage this living room in a scandinavian style."* Claude calls the virtual_staging tool with the right parameters and returns a downloadable, photorealistic image. No manual editing, no design software.

Is this AI virtual staging free?

The MCP server itself is open source and MIT‑licensed, so you can self‑host it at no cost. The image processing runs on the AI HomeDesign API and uses your own API key.

Does it work with clients other than Claude?

Yes. It speaks standard MCP over streamable HTTP, so any MCP‑compatible client — Claude Desktop, Claude in the browser, Cursor, and others — can use it.

What is the difference between virtual staging and virtual restaging?

Virtual staging furnishes an *empty* room. Virtual restaging swaps the furniture in an *already‑furnished* room. Use interior_design when you want to redesign a furnished room completely rather than just replace the furniture.

Learn more

🔌 Connect in one click: aihomedesign.com/mcp
🌐 Website: aihomedesign.com
📖 Model Context Protocol: modelcontextprotocol.io

Contributing

Issues and pull requests are welcome. Please open an issue to discuss substantial changes first.

License

Released under the MIT License.

Keywords: MCP server · Model Context Protocol · Claude MCP · Anthropic MCP · MCP tools · virtual staging · AI virtual staging · virtual staging software · home staging · virtual staging for realtors · AI home design · AI interior design · real estate photography · real estate photo editing · virtual restaging · day to dusk · image enhancement · item removal · real estate AI · PropTech.

AI HomeDesign MCP

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“设计、图片与音频”中的其他服务器比较i

常见问题

替代选择

Figma Context MCP

Claude Real Video

Figma MCP Server

作者的 README

AI HomeDesign MCP Server — AI Virtual Staging, Home Staging & Interior Design for Claude

What is this?

Why virtual staging and home staging over MCP?

Available tools

Quick start

Option A — Connect to the hosted server (no setup)

Option B — Self‑host with Docker

Option C — Run locally with Python

Configuration

Security & multi‑tenant design

How it works

Tech stack

FAQ

What is an MCP server?

How do you virtually stage a photo with this?

Is this AI virtual staging free?

Does it work with clients other than Claude?

What is the difference between virtual staging and virtual restaging?

Learn more

Contributing

License