MeltFlex AI
NPM · MELTFLEX-MCP · 2 COMPONENTS
AI interior design — restyle rooms, place furniture, and virtually stage spaces from a photo.
Available components
Last scanned (14 hours ago)
Scores higher than 59% of npm servers
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 78 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability68
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1339 tokens (~223/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 0
- Security disclosure: unverified → fail ▼ functional
- 19 Nov 26 +1
- Stability: 0.97 → pass security
- 18 Nov 26 −1
- Security disclosure: fail → unverified ▼ functional
- Stability: pass → 0.97 functional
- 12 Nov 26 +1
- Stability: 0.97 → pass security
- Package version: 0.2.1 → 0.6.0 functional
- 10 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +4
- Source repository: unverified → pass ▲ security
- Stability: pass → 0.90 functional
- 8 Nov 26 −6
- Provenance: pass → unverified ▼ security
- 7 Nov 26 +15
- Malware scan: unverified → pass ▲ security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/meltflex-mcp@0.6.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_credits Check MeltFlex credits ~27
Check the current MeltFlex credit balance and the per-operation credit costs for the authenticated account.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
floorplan_to_3d Convert floorplan to 3D model ~147
Convert a flat 2D floorplan image into a downloadable GLB 3D model. Costs 100 MeltFlex credits. The .glb is downloaded to disk and the file path is returned. Best results come from a clean, high-contrast floorplan with clear walls.
| Name | Type | Req | Description |
|---|---|---|---|
| image | string | yes | Source 2D floorplan image (JPEG, PNG or WebP): a local file path, an http(s) URL, or a data:image/...;base64,... URL. |
| output_path | string | – | Where to save the .glb. Defaults to ./meltflex-output/model-<timestamp>.glb in the current working directory. |
No output schema declared.
No examples provided.
furniture_to_3d Convert a furniture photo to a 3D model ~218
Turn ONE photo of a furniture piece (sofa, chair, table, lamp…) into a textured, downloadable GLB 3D model. Costs 75 MeltFlex credits (refunded if the build fails). Takes about 2–3 minutes; this tool waits for the model. Best input: one piece, front three-quarter view, plain or white background, nothing cropped. The .glb is downloaded to disk and the file path is returned, along with signed USDZ/FBX/OBJ links (valid ~72 h).
| Name | Type | Req | Description |
|---|---|---|---|
| image | string | yes | Photo of ONE furniture piece: a local file path, an http(s) URL, or a data:image/...;base64,... URL. |
| output_path | string | – | Where to save the .glb. Defaults to ./meltflex-output/furniture-<timestamp>.glb in the current working directory. |
| textured | boolean | – | Default true (baked PBR textures). false → bare geometry only: faster, smaller, same price. |
No output schema declared.
No examples provided.
generate_interior Generate interior design ~460
Transform a room photo into a redesigned, photorealistic interior using MeltFlex AI. Provide a source room photo (local file path, http(s) URL, or data:image URL) and a prompt describing the desired style or changes. Optionally provide reference furniture/decor images to place specific products into the room. Supports output quality (512/1K/2K), a design level (lite/quick/pro), region editing via a red mask, and batch generation of up to 3 variations. Costs 10 credits per image (lite −2, pro +5), multiplied by the number of variations. Each result is saved to disk and the file paths are returned.
| Name | Type | Req | Description |
|---|---|---|---|
| design_level | string | – | Effort tier: "lite" (faster & cheaper, −2 credits), "quick" (default), or "pro" (most detailed, HIGH thinking, +5 credits). |
| image | string | yes | Source room photo: a local file path, an http(s) URL, or a data:image/...;base64,... URL. |
| mask | boolean | – | Region edit. When true, the source image must have the area to change painted SOLID RED; the prompt is applied ONLY to those red-marked regions and everything else is left untouched. |
| output_path | string | – | Where to save the result. Defaults to ./meltflex-output/interior-<timestamp>.<ext>. For a batch, an index (-1, -2, …) is appended so files never collide. |
| prompt | string | yes | What to do to the room, e.g. "Redesign in warm Scandinavian style with light oak floors and a beige linen sofa". Room structure (walls, windows, doors) is preserved unless you say otherwise. |
| reference_images | array | – | Optional furniture/decor reference images (file paths or URLs) whose exact appearance should be placed into the room. |
| resolution | string | – | Output quality / resolution. "512" (fast), "1K", or "2K" (sharpest). Defaults to model auto. |
| variations | integer | – | Number of variations to generate in one batch: 1–3 (default 1). Credits are charged per image. |
No output schema declared.
No examples provided.
generate_video Generate interior walkthrough video ~238
Animate a still image (a MeltFlex render or any interior photo) into a short cinematic walkthrough video using Veo 3.1. Costs 100 MeltFlex credits for a 4-second clip or 150 for 8 seconds. Generation is asynchronous and can take 30–120 seconds. The MP4 is downloaded to disk and the file path is returned.
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | "16:9" (default, landscape) or "9:16" (vertical). |
| duration_seconds | number | – | Clip length: 4 (100 credits, default) or 8 (150 credits). |
| image | string | yes | Source still image: a local file path, an http(s) URL, or a data:image/...;base64,... URL. |
| output_path | string | – | Where to save the .mp4. Defaults to ./meltflex-output/walkthrough-<timestamp>.mp4 in the current working directory. |
| prompt | string | – | Optional camera/mood direction, e.g. "Slow dolly forward, then pan left to the window". Defaults to a slow cinematic dolly. |
No output schema declared.
No examples provided.
generate_world Generate an explorable 3D world from a room photo ~249
Turn ONE interior photo or render (e.g. a generate_interior result) into an explorable 3D world (Gaussian splats) you can look around and walk through from the camera's viewpoint. Costs 30 MeltFlex credits for a "draft" world (~1 min) or 200 for "hd" (~5 min, sharper up close); refunded if the build fails. This tool waits for the world. Returns the worldId (permanent), a hosted viewer link, and the .spz splat file downloaded to disk. The .spz links expire after a few days — keep the worldId.
| Name | Type | Req | Description |
|---|---|---|---|
| image | string | yes | Room photo or render: a local file path, an http(s) URL, or a data:image/...;base64,... URL. |
| model | string | – | "draft" (30 credits, ~1 min, default) or "hd" (200 credits, ~5 min). |
| name | string | – | Optional label for the world. |
| output_path | string | – | Where to save the .spz splat file. Defaults to ./meltflex-output/world-<timestamp>.spz in the current working directory. |
No output schema declared.
No examples provided.
How do I install the MeltFlex AI MCP server?
MeltFlex AI runs locally as an npm package, launched with npx -y meltflex-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · meltflex-mcp
claude mcp add meltflexdevs-meltflex -- npx -y meltflex-mcp
What is the MeltFlex AI MCP server?
MeltFlex AI is an MCP server listed in the public MCP registry as io.github.MeltFlexDevs/meltflex. AI interior design, restyle rooms, place furniture, and virtually stage spaces from a photo. This page covers its npm package (meltflex-mcp).
Is the MeltFlex AI MCP server safe to use?
MeltFlex AI scores 78 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the MeltFlex AI MCP server expose?
MeltFlex AI exposes 6 tools: generate_interior, generate_video, floorplan_to_3d, furniture_to_3d, generate_world, check_credits. Their descriptions and schemas cost roughly 1,339 tokens of context every time the server is loaded.
Is the MeltFlex AI MCP server still maintained?
MeltFlex AI is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the MeltFlex AI MCP server under?
MeltFlex AI declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the MeltFlex AI MCP server?
VerifyMCP ran 16 checks on MeltFlex AI, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.