T
TJLDC/roomvana-mcp
An MCP server for Roomvana — AI home design for houses, yards and rooms.
更新 2026-11-07
在 GitHub 查看 ↗直链 · 无中转页
安装与配置
远端端点(Claude Desktop / Cursor / Windsurf 共用 mcpServers)
{
"mcpServers": {
"tjldc-roomvana-mcp": {
"url": "https://api.roomvana.co/mcp"
}
}
}把这段粘进 Claude Desktop / Cursor 的 mcpServers 配置即可。端点来自公开证据,我们没有替你安装或托管它。 官方 Registry 记录:这个端点没有列出任何请求头。这不等于免密 —— 以项目文档为准。
VS Code(.vscode/mcp.json —— 键名是 servers,远程要 type: http)
{
"servers": {
"tjldc-roomvana-mcp": {
"type": "http",
"url": "https://api.roomvana.co/mcp"
}
}
}VS Code 的配置文件和另外三家不同:顶层键是 <code>servers</code>,远程端点还要写 <code>"type": "http"</code>。复制到 .vscode/mcp.json。
Claude Code(命令行)
claude mcp add --transport http tjldc-roomvana-mcp https://api.roomvana.co/mcp
Claude Code 不收 JSON 文件,用这条命令直接加。
配置文件在:macOS
~/Library/Application Support/Claude/claude_desktop_config.json、Windows %APPDATA%\Claude\claude_desktop_config.json、Linux ~/.config/Claude/claude_desktop_config.json。配置项的键名以你的客户端为准:客户端与 CLI- ★ 数取值
- 0 ★ · TJLDC/roomvana-mcp · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 收录自 punkpeye/awesome-mcp-servers 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
- 收录与活跃
- 收录于 2026-11-18 · 最近见到 2026-11-20 · 共见到 3 次 · 被 3 个来源列出
- 评分构成
- 综合分 300 · 3 个来源 · mcp
常见问题(答案都来自我们的记录)
怎么安装?
我们【没有】从该仓库取到安装命令(我们的 install 覆盖率只有约 4%)。请看它的 README 或 releases 页。
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
TJLDC/roomvana-mcp;我们收录于 2026-11-18;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。README 原文(英文,未翻译) · 在 GitHub 读完整 README →
# Roomvana MCP server
以下摘录自该仓库的 README(片段)
An MCP server for Roomvana — AI home design for houses, yards and rooms. It lets an AI assistant browse the room types and design styles Roomvana supports and hand the user a studio link with their choices pre-selected. Upload a photo of your house, yard or any room and see it redesigned at roomvana.ai.
Read-only and no sign-in required: this server never uploads photos or spends credits. The actual redesign happens on the website.
## Tools
| Tool | What it does |
| list_design_styles | Lists the design styles Roomvana can render (modern, japandi, industrial, coastal, …), each with a short description. |
| list_room_types | Lists the rooms and outdoor spaces Roomvana can redesign — interior rooms, house exterior, and garden/patio/backyard. |
| design_a_room | Returns a roomvana.ai studio link with the chosen room and style pre-selected; validates both against Roomvana's live catalog. |
## Install
Requires Node.js 18+.
json
"mcpServers": {
"roomvana": {
"command": "npx",
"args": ["-y", "roomvana-mcp"]
Add that to your MCP client config (Claude Desktop: claude_desktop_config.json; other clients: their MCP config file), then restart the client.
Or with the Python package, using uv:
json
"mcpServers": {
"roomvana": {
"command": "uvx",
"args": ["roomvana-mcp"]
The Python implementation lives in python/ and is published on PyPI as roomvana-mcp. Both implementations expose the same three tools and need no API key.
### From source
TypeScript:
bash
npm install
npm run build
npm start
Python:
bash
cd python && uv run roomvana-mcp
## Example
> "I want to redo my bedroom in a japandi style."
The assistant calls design_a_room with room=bedroom, style=japandi and returns:
https://roomvana.ai/design?room=bedroom&style=japandi
Open it, upload a photo of the room, and generate a redesign. Your walls, windows and layout stay put — only the look changes.
## How it works
The list of supported rooms and styles is fetched live from Roomvana's public catalog endpoint (https://api.roomvana.co/options), so the server never offers something Roomvana can't render. If that endpoint is unreachable, it falls back to a bundled snapshot.
Read-only and no sign-in required: this server never uploads photos or spends credits. The actual redesign happens on the website.
## Tools
| Tool | What it does |
| list_design_styles | Lists the design styles Roomvana can render (modern, japandi, industrial, coastal, …), each with a short description. |
| list_room_types | Lists the rooms and outdoor spaces Roomvana can redesign — interior rooms, house exterior, and garden/patio/backyard. |
| design_a_room | Returns a roomvana.ai studio link with the chosen room and style pre-selected; validates both against Roomvana's live catalog. |
## Install
Requires Node.js 18+.
json
"mcpServers": {
"roomvana": {
"command": "npx",
"args": ["-y", "roomvana-mcp"]
Add that to your MCP client config (Claude Desktop: claude_desktop_config.json; other clients: their MCP config file), then restart the client.
Or with the Python package, using uv:
json
"mcpServers": {
"roomvana": {
"command": "uvx",
"args": ["roomvana-mcp"]
The Python implementation lives in python/ and is published on PyPI as roomvana-mcp. Both implementations expose the same three tools and need no API key.
### From source
TypeScript:
bash
npm install
npm run build
npm start
Python:
bash
cd python && uv run roomvana-mcp
## Example
> "I want to redo my bedroom in a japandi style."
The assistant calls design_a_room with room=bedroom, style=japandi and returns:
https://roomvana.ai/design?room=bedroom&style=japandi
Open it, upload a photo of the room, and generate a redesign. Your walls, windows and layout stay put — only the look changes.
## How it works
The list of supported rooms and styles is fetched live from Roomvana's public catalog endpoint (https://api.roomvana.co/options), so the server never offers something Roomvana can't render. If that endpoint is unreachable, it falls back to a bundled snapshot.
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/tjldc-roomvana-mcp/)
- 来源
- awesome · https://github.com/TJLDC/roomvana-mcp
- 按领域浏览
- MCP 服务
- 收录来源
- 3 个独立来源
- 收录于
- 今天
更多 MCP 服务器
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。