Enables AI agents to perform photorealistic interior and exterior design, generate 3D models from photos, and create cinematic video walkthroughs.
Also known as MeltFlexDevs/skills, skills, meltflex-mcp
- Stars
- 11
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.6.0
- Last commit
- Nov 6, 2026
- License
- MIT
What is MeltFlex AI MCP?
MeltFlex AI enables AI agents to perform photorealistic interior and exterior design, generate 3D models from photos, and create cinematic video walkthroughs.
Summary generated from the project's README
About MeltFlex AI MCP server
MeltFlex AI provides a suite of tools for AI agents to perform high-fidelity interior and exterior design tasks. It allows users to restyle rooms, redesign kitchens or bathrooms, and modify architectural elements like floors, walls, stairs, doors, and windows using single photos. The server supports various modes including virtual staging, garden landscaping, and turning 3D drafts into photorealistic renders.
Beyond 2D imagery, the platform generates 3D assets and immersive environments. Developers can use it to convert furniture photos into GLB models, transform 2D floorplans into 3D models, or create explorable 3D worlds from room photos. It also supports cinematic video walkthroughs in MP4 format. The system is designed for use with AI agents like Claude Code, Cursor, and Hermes via MCP or Markdown-based skills.
Users must authenticate with a MeltFlex API key and maintain an active paid subscription. Each generation consumes account credits. The MCP server simplifies the workflow by providing tools such as generate_interior, generate_video, and furniture_to_3d, while automatically handling long-running build polling and file saving.
What you can do with it
- 1Redesign architectural spacesAsk an AI agent to restyle a room, change wall textures, or redesign a garden from a single uploaded photo.
- 2Generate 3D furniture modelsConvert a photograph of a specific piece of furniture into a textured GLB 3D model.
- 3Place specific products in scenesInstruct an agent to place real furniture items into a room photo while matching their exact colors and proportions.
Written from the project's README. Every use case is checked against a quote from it.
How to install MeltFlex AI MCP
Formats verified 10 Nov 2026Install MeltFlex AI MCP in Claude Code
$ claude mcp add --env MELTFLEX_API_KEY=<YOUR_MELTFLEX_API_KEY> skills -- npx -y meltflex-mcpInstall MeltFlex AI MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"skills": {
"command": "npx",
"args": [
"-y",
"meltflex-mcp"
],
"env": {
"MELTFLEX_API_KEY": "<YOUR_MELTFLEX_API_KEY>"
}
}
}
}Install MeltFlex AI MCP in VS Code
.vscode/mcp.json
{
"servers": {
"skills": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"meltflex-mcp"
],
"env": {
"MELTFLEX_API_KEY": "<YOUR_MELTFLEX_API_KEY>"
}
}
}
}Install MeltFlex AI MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"skills": {
"command": "npx",
"args": [
"-y",
"meltflex-mcp"
],
"env": {
"MELTFLEX_API_KEY": "<YOUR_MELTFLEX_API_KEY>"
}
}
}
}Install MeltFlex AI MCP in Codex
~/.codex/config.toml
[mcp_servers.skills] command = "npx" args = ["-y", "meltflex-mcp"] [mcp_servers.skills.env] MELTFLEX_API_KEY = "<YOUR_MELTFLEX_API_KEY>"
Install MeltFlex AI MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"skills": {
"command": "npx",
"args": [
"-y",
"meltflex-mcp"
],
"env": {
"MELTFLEX_API_KEY": "<YOUR_MELTFLEX_API_KEY>"
}
}
}
}Configuration
MELTFLEX_API_KEYRequiredSecretYour MeltFlex API key (mf_sk_...). Requires an active MeltFlex subscription — generate a key at https://www.meltflexai.com/settings.
| Name | Description | |
|---|---|---|
| MELTFLEX_API_KEY | Your MeltFlex API key (mf_sk_...). Requires an active MeltFlex subscription — generate a key at https://www.meltflexai.com/settings. | RequiredSecret |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubMeltFlex 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.
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
| Skill | Invoke | Description |
|---|---|---|
| meltflex-design | /meltflex:design |
Restyle 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:furniture |
Place specific real furniture/decor products into a room photo, matching their exact colors, materials, and proportions (up to 10 reference items). |
| meltflex-3d | /meltflex:3d |
3D 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:embed |
Put 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:
| Mode | What it's for |
|---|---|
restyle |
Change a room's style or theme |
virtual_staging |
Furnish an empty room |
layout_boost |
Rearrange existing furniture into a better layout |
declutter |
Clean up / depersonalize a space |
exterior |
Building facade / house exterior |
garden |
Landscaping and outdoor design |
wall_texture |
Change wall material or finish |
floor_restyle |
Change the flooring |
stairs |
Restyle a staircase in place |
doors |
Swap interior doors |
windows |
Swap window frames / glazing |
kitchen |
Whole kitchen redesign |
bathroom |
Whole bathroom redesign |
photo_to_render |
Turn a 3D draft / SketchUp shot into a photo |
seasonal |
Time-of-day / seasonal / lighting variation |
region_edit |
Change 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.
| Output | Endpoint | Credits | Time | MCP tool · CLI |
|---|---|---|---|---|
| Cinematic walkthrough video (MP4, Veo 3.1) | POST /api/v1/video |
100 (4s) / 150 (8s) | ~1 min | generate_video · meltflex video |
| Floorplan → rendered 3D picture (PNG) | POST /api/v1/floorplan-to-3d output: "render" |
10 | ~20 s | REST only |
| Floorplan → GLB 3D model | POST /api/v1/floorplan-to-3d output: "model" |
100 | ~3 min | floorplan_to_3d · meltflex floorplan |
| Furniture photo → GLB 3D model (+ USDZ/FBX/OBJ) | POST /api/v1/furniture-3d |
75 | 2–3 min | furniture_to_3d · meltflex furniture |
| Photo → explorable 3D world (.spz + viewer link) | POST /api/v1/world |
30 (draft) / 200 (hd) | ~1 / ~5 min | generate_world · meltflex world |
Full reference with response bodies and three.js / Spark loader snippets: https://www.meltflexai.com/api.
Quick Reference
| What you want | Skill | Note |
|---|---|---|
| Restyle a room from a photo | meltflex-design |
Pick a mode, write a specific prompt |
| Furnish an empty room | meltflex-design |
virtual_staging mode |
| Place a specific sofa/bed/table | meltflex-furniture |
Pass product images as references |
| Redesign a house exterior or garden | meltflex-design |
exterior / garden mode |
| Swap flooring or wall finish | meltflex-design |
floor_restyle / wall_texture (attach the material as a reference) |
| Restyle stairs, doors or windows | meltflex-design |
stairs / doors / windows mode |
| Redesign a kitchen or bathroom | meltflex-design |
kitchen / bathroom mode |
| Turn a 3D draft into a photo | meltflex-design |
photo_to_render mode |
| Change only one marked area | meltflex-design |
region_edit — paint it red, mask: true |
| Sharper output / several options | meltflex-design |
resolution: "2K", designLevel: "pro", variations: 3 |
| Cinematic video walkthrough | meltflex-design |
POST /api/v1/video (100–150 credits) |
| 3D model of a furniture piece | meltflex-3d |
POST /api/v1/furniture-3d (75 credits) |
| 2D floorplan → 3D model / 3D picture | meltflex-3d |
POST /api/v1/floorplan-to-3d (100 / 10 credits) |
| Walk through a room in 3D | meltflex-3d |
POST /api/v1/world (30 draft / 200 hd) |
| Check credit balance | — | meltflex credits (CLI) or the MCP check_credits tool |
Embed on your website
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"
></iframe>
On a shop's product page, add ?product=<product page address> 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 meltflex-mcp auth login
mcp_servers:
meltflex:
command: npx
args: ["-y", "meltflex-mcp"]
Start hermes chat (or run /reload-mcp in a session) to load the six MeltFlex tools. Full guide: https://www.meltflexai.com/mcp.
Going further
- API docs: https://www.meltflexai.com/api
- CLI: https://www.meltflexai.com/cli —
meltflex generatefrom your terminal - MCP server: https://www.meltflexai.com/mcp —
npx -y meltflex-mcp - Cookbook: COOKBOOK.md · Changelog: CHANGELOG.md
Security
The skills never contain a key. Each user supplies their own mf_sk_ key via MELTFLEX_API_KEY; generations spend that user's own credits. Credits, auth, and rate limits are all enforced server-side. Never commit your key — revoke it anytime in settings.
License
MIT — see LICENSE. Contributions welcome — see CONTRIBUTING.md.
MeltFlex AI MCP questions
How do I add MeltFlex AI MCP to Claude Code?
Run claude mcp add --env MELTFLEX_API_KEY=<YOUR_MELTFLEX_API_KEY> skills -- npx -y meltflex-mcp in your terminal. Add --scope user to make it available in every project.
How do I add MeltFlex AI MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What kind of 3D outputs can I generate?
The server can create GLB 3D models from furniture photos or 2D floorplans, and transform room photos into explorable 3D worlds.
Does the service require a paid subscription?
Yes, you need an active paid subscription to use the API key.