3d-scene-mcpSAFE
Build and manipulate 3D scenes from natural language via AI agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/scene-mcp
Speak 3D worlds into being — turn one sentence into a placed diorama from any AI agent.
A Model Context Protocol server that gives any AI assistant the three.ws diorama pipeline over stdio. Describe a world in a sentence andcompose_scenereturns a placed plan — mood, palette, ground, and a set of single-object forge prompts — ready to build into an orbitable 3D scene. Browse saved worlds withget_sceneandlist_scenes.
This is the companion to the three.ws avatar one-liner: avatars give you a character; scenes give you a world. No API key, no signer, no payment — every call hits the public /api/diorama endpoint.
Install
npm install @three-ws/scene-mcp
Or run with npx (no install):
npx @three-ws/scene-mcp
Quick start
Claude Code, one line:
claude mcp add scene -- npx -y @three-ws/scene-mcp
Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):
{
"mcpServers": {
"scene": {
"command": "npx",
"args": ["-y", "@three-ws/scene-mcp"]
}
}
6a207b3bfbd3OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add scene-mcp -- npx -y @three-ws/[email protected]
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
@modelcontextprotocol/sdk, zod
- `.env` files are gitignored; never commit credentials, and read configuration from environment variables.
Gates applied: no_behavioural_pass.
6a207b3bfbd3full audit observations/trust-audit/mcp-server/nirholas__3d-scene-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 6a207b3bfbd3 | SAFE | B | 89 | first audit |
Questions
What is the 3d-scene-mcp MCP server?
Build and manipulate 3D scenes from natural language via AI agents.
Is 3d-scene-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does 3d-scene-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does 3d-scene-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/scene-mcp at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (6a207b3bfbd3), read on 2026-10-10. The repository is watched and re-audited when it changes.