原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

MeltFlex AI

作者:MeltFlexDevs版本 0.2.1i★ –i在你的电脑上运行
注册名称io.github.MeltFlexDevs/meltflex

安装

概览

作者提供的说明(英文原文)

AI interior design — restyle rooms, place furniture, and virtually stage spaces from a photo.

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。

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: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 设计、图片与音频
  • 你需要填写:MELTFLEX_API_KEY

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

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 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "meltflex": {
      "command": "npx",
      "args": [
        "-y",
        "meltflex-mcp"
      ],
      "env": {
        "MELTFLEX_API_KEY": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add meltflex --env MELTFLEX_API_KEY=your-value -- npx -y meltflex-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

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

{
  "mcpServers": {
    "meltflex": {
      "command": "npx",
      "args": [
        "-y",
        "meltflex-mcp"
      ],
      "env": {
        "MELTFLEX_API_KEY": "your-value"
      }
    }
  }
}

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。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "meltflex": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "meltflex-mcp"
      ],
      "env": {
        "MELTFLEX_API_KEY": "your-value"
      }
    }
  }
}

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。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • MELTFLEX_API_KEY 机密 必填 env
    Your MeltFlex API key (mf_sk_...). Requires an active MeltFlex subscription — generate a key at https://www.meltflexai.com/settings.

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

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

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6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 MeltFlexDevs 验证,该账户拥有此仓库

  • … 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

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

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 2164 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 2164 个服务器的 11% 更新
  • 基础检查结果等于或优于此分类中其他 2164 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

MeltFlex AI 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?

你需要填写:MELTFLEX_API_KEY

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.2.1)于5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。你的电脑上还需要有 Node.js。

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。

MeltFlex AI Skills

AI agent skills for photorealistic interior and exterior design and 3D via MeltFlex AI — restyle rooms, place real furniture, swap floors, walls, stairs, doors and windows, redesign kitchens, bathrooms, facades and gardens, and turn 3D drafts into photos, all from a single photo. Then go further: cinematic video walkthroughs, 2D floorplan → 3D model or rendered 3D picture, furniture photo → GLB 3D model, and photo → explorable 3D world. Works with Claude Code, Hermes, Cursor, Codex, Cline, and other AI agents that load Markdown-based skills or speak MCP.

Each user authenticates with their own MeltFlex API key; every generation is billed to their account credits. The skills call the public MeltFlex API directly, so there's nothing extra to install.

Interior redesign · floor restyle from a material · garden design — a few of the 16 image modes, all from one photo.

Furniture photo → 3D model · room render → explorable 3D world · 2D floorplan → 3D model. Real outputs of /api/v1/furniture-3d , /api/v1/world and /api/v1/floorplan-to-3d .

Install

Pick one. Each method sets up the skills for your agent.

npx skills — recommended, cross-agent
npx skills add MeltFlexDevs/skills
GitHub CLI (v2.90+)
gh skill install MeltFlexDevs/skills
Claude Code marketplace

Inside Claude Code:

/plugin marketplace add MeltFlexDevs/skills

/plugin install meltflex@meltflex

Setup script

Universal fallback:

git clone --depth 1 https://github.com/MeltFlexDevs/skills.git

cd skills ./setup

More options in INSTALL.md. Agent-driven install (paste into your agent): INSTALL_FOR_AGENTS.md. Cline and other MCP-settings agents: llms-install.md.

Authenticate

You need an active subscription (any paid plan) — without one the key won't work. After subscribing at https://www.meltflexai.com/settings, open account settings → API Key under Profile, then Generate API Key (shown once — copy it):

Then expose it:

export MELTFLEX_API_KEY="mf_sk_xxxxxxxxxxxx"

If you use the MCP server / CLI, you can skip the copy-paste and sign in from the browser instead: npx -y meltflex-mcp auth login opens https://www.meltflexai.com/cli/authorize, mints a key from your signed-in session and stores it in ~/.meltflex/config.json (chmod 600).

Skills

SkillInvokeDescription
meltflex-design/meltflex:designRestyle a room, facade or garden; swap floors, walls, stairs, doors or windows; redesign a kitchen or bathroom; boost a layout; turn a 3D draft into a photo. 16 prompt-driven modes with quality levels, region editing and batches, plus video walkthroughs via the API.
meltflex-furniture/meltflex:furniturePlace specific real furniture/decor products into a room photo, matching their exact colors, materials, and proportions (up to 10 reference items).
meltflex-3d/meltflex:3d3D output: a furniture photo → GLB model, a 2D floorplan → GLB model or rendered 3D picture, a room photo → explorable 3D world (splat + hosted viewer). Handles the long-build polling.
meltflex-embed/meltflex:embedPut the design tool on your own website as an iframe: visitors design their room, or place your shop's products in it, without an account. Installs the code in HTML, React, Vue, Shopify or WordPress and fixes a blank frame. No API key.

Image skills are self-contained: a room photo in, a photorealistic redesign out, 10 credits per image (auto-refunded on failure).

Image modes

meltflex-design — 16 modes, each the same POST /api/v1/generate endpoint with a mode-tuned prompt:

ModeWhat it's for
restyleChange a room's style or theme
virtual_stagingFurnish an empty room
layout_boostRearrange existing furniture into a better layout
declutterClean up / depersonalize a space
exteriorBuilding facade / house exterior
gardenLandscaping and outdoor design
wall_textureChange wall material or finish
floor_restyleChange the flooring
stairsRestyle a staircase in place
doorsSwap interior doors
windowsSwap window frames / glazing
kitchenWhole kitchen redesign
bathroomWhole bathroom redesign
photo_to_renderTurn a 3D draft / SketchUp shot into a photo
seasonalTime-of-day / seasonal / lighting variation
region_editChange only one area — paint it solid red, send mask: true

Optional fields on every image call: resolution (512 / 1K / 2K), designLevel (lite −2 cr · quick · pro +5 cr), variations (1–3 per call, charged per image), up to 10 referenceImageUrls.

Video & 3D

Same key, five more outputs. The three 3D builds can take minutes; they answer HTTP 202 + a poll URL when they outlive the request, and /meltflex:3d shows how to poll.

OutputEndpointCreditsTimeMCP tool · CLI
Cinematic walkthrough video (MP4, Veo 3.1)POST /api/v1/video100 (4s) / 150 (8s)~1 mingenerate_video · meltflex video
Floorplan → rendered 3D picture (PNG)POST /api/v1/floorplan-to-3d output: "render"10~20 sREST only
Floorplan → GLB 3D modelPOST /api/v1/floorplan-to-3d output: "model"100~3 minfloorplan_to_3d · meltflex floorplan
Furniture photo → GLB 3D model (+ USDZ/FBX/OBJ)POST /api/v1/furniture-3d752–3 minfurniture_to_3d · meltflex furniture
Photo → explorable 3D world (.spz + viewer link)POST /api/v1/world30 (draft) / 200 (hd)~1 / ~5 mingenerate_world · meltflex world

Full reference with response bodies and three.js / Spark loader snippets: https://www.meltflexai.com/api.

Quick Reference

What you wantSkillNote
Restyle a room from a photomeltflex-designPick a mode, write a specific prompt
Furnish an empty roommeltflex-designvirtual_staging mode
Place a *specific* sofa/bed/tablemeltflex-furniturePass product images as references
Redesign a house exterior or gardenmeltflex-designexterior / garden mode
Swap flooring or wall finishmeltflex-designfloor_restyle / wall_texture (attach the material as a reference)
Restyle stairs, doors or windowsmeltflex-designstairs / doors / windows mode
Redesign a kitchen or bathroommeltflex-designkitchen / bathroom mode
Turn a 3D draft into a photomeltflex-designphoto_to_render mode
Change only one marked areameltflex-designregion_edit — paint it red, mask: true
Sharper output / several optionsmeltflex-designresolution: "2K", designLevel: "pro", variations: 3
Cinematic video walkthroughmeltflex-designPOST /api/v1/video (100–150 credits)
3D model of a furniture piecemeltflex-3dPOST /api/v1/furniture-3d (75 credits)
2D floorplan → 3D model / 3D picturemeltflex-3dPOST /api/v1/floorplan-to-3d (100 / 10 credits)
Walk through a room in 3Dmeltflex-3dPOST /api/v1/world (30 draft / 200 hd)
Check credit balance—meltflex credits (CLI) or the MCP check_credits tool

Embed on your website

Live on the Kondela furniture shop: shoppers place its own products in a photo of their room, on the shop's own page.

No API key and no backend: build an embed in the Website Embed Builder (your domain, logo, colour, language, and for shops your product feed), then paste one iframe. Visitors design their room on your page without an account; each design uses 10 credits from your account. Any account gets the code and 10 free designs; after that it runs on an Enterprise plan.

<iframe

src="https://widget.meltflexai.com/YOUR_EMBED_ID" title="AI Interior Design by MeltFlex" width="100%" height="720" style="border:0;border-radius:12px;max-width:100%;" allow="clipboard-write" loading="lazy"

On a shop's product page, add ?product= and the tool opens with that product. /meltflex:embed installs the code in your project (HTML, React / Next.js, Vue, Shopify, WordPress), sets the frame-src rule if your site has a Content Security Policy, and walks through a blank frame. Guide: https://www.meltflexai.com/api#embed.

Use with the MCP server

Agents that prefer tool calls over scripted API calls can run the meltflex-mcp server (npm, stdio). It exposes six tools — generate_interior, generate_video, floorplan_to_3d, furniture_to_3d, generate_world, check_credits — and handles polling and saving files to disk.

npx -y meltflex-mcp auth login              # or: npx -y meltflex-mcp auth mf_sk_xxxxxxxx

claude mcp add meltflex -- npx -y meltflex-mcp

Any MCP client works with the same shape (command: npx, args: ["-y", "meltflex-mcp"], optional env.MELTFLEX_API_KEY). The same package is a terminal CLI: meltflex generate | video | floorplan | furniture | world | credits. A Claude Desktop extension bundle lives in mcpb/.

Hermes

Hermes (Nous Research) speaks MCP, so it runs MeltFlex through the same server.

From the catalog (once merged into the Hermes catalog):

hermes mcp install meltflex

Manually — sign in once, then add the server to ~/.hermes/config.yaml:

npx -y me

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx