agentmods.dev

worldlabs

worldlabs is a skill for Claude Code from sandraschi/worldlabs-mcp. It costs 43 tokens per session (1,592 once invoked), scanned A, original, MIT.

A 3D world-generation tool creates navigable scenes from text, images, or video using World Labs Marble, then lets people browse and spatially narrate them.

In plain words
What is it for?
It is for generating, viewing, organising, and describing 3D Gaussian-splat worlds, including scenes from the World Labs community gallery.
Why use it?
It provides a way to turn media or descriptions into explorable 3D scenes instead of making those scenes by hand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the worldlabs-mcp plugin — 2 skills shipped together

not rated 24repo today A scan 43 tokens original MIT

Good fit It is for generating, viewing, organising, and describing 3D Gaussian-splat worlds, including scenes from the World Labs community gallery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandraschi/worldlabs-mcp/worldlabs
View source ↗ sandraschi/worldlabs-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sandraschi/worldlabs-mcp --skill worldlabs
Clone the repo
git clone --depth 1 https://github.com/sandraschi/worldlabs-mcp

Made for: Claude Code.

Or install worldlabs-mcp, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for worldlabs

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandraschi/worldlabs-mcp/worldlabs/github.svg)](https://agentmods.dev/skills/sandraschi/worldlabs-mcp/worldlabs)
Your own site
<a href="https://agentmods.dev/skills/sandraschi/worldlabs-mcp/worldlabs"><img src="https://agentmods.dev/badge/skills/sandraschi/worldlabs-mcp/worldlabs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for worldlabs

Your own site · 80×15
<a href="https://agentmods.dev/skills/sandraschi/worldlabs-mcp/worldlabs"><img src="https://agentmods.dev/badge/skills/sandraschi/worldlabs-mcp/worldlabs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01592
Opus 5.5 $0.00017 $0.00637
Sonnet 5.5 $0.00009 $0.00318
Haiku 4.5 $0.00004 $0.00159

Measured 23d ago against content hash 2cdfc31efc01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

worldlabs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/worldlabs/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

World Labs MCP — domain skill

MCP gateway to World Labs Marble 1.1 (world generation) + Spark 2.0 (streaming splat viewer with HRTF spatial audio). Backend bridge on :10865, webapp on :10864. 23 MCP tools, 2 Prefab cards, 2 resources, 2 prompts.

Agent vs human routing

  • Agent (you): call the MCP tools directly. Poll async work with get_operation; never claim a world exists before done=true with a world_id. Credit owners when reusing gallery prompts.
  • Human (Sandra): point at the webapp — Architect (/architect) for generation, Inbox (/inbox) for the action queue, Library (/library) for finished worlds, Spark viewer (/spark-viewer) for walkthroughs.

Tool catalog (real operation names)

Generate: generate_world_from_text, generate_world_from_image (is_panorama for 360 equirectangular), generate_world_from_multi_image (min 2 images + matching azimuths_deg), generate_world_from_video, upload_and_generate (local file end-to-end, 100 MB cap), plus the manual two-step prepare_media_upload → generate_world_from_media_asset. seed pins deterministic output; tags organises; disable_recaption stops the API rewriting prompts. Default model marble-1.1 (1500 credits, ~1-3 min); marble-1.1-plus auto-expands (1500 + 300/cube, slower).

Poll: get_operation (single poll, raises on failed ops), wait_for_world (blocking ≤90 s — suits marble-1.1 only; loop get_operation for plus).

Manage: list_worlds (paginated), get_world (SPZ/GLB/panorama/ thumbnail/CDN links are time-limited — download promptly), delete_world (irreversible, destructive).

Spatial (needs bridge :10865 + open Spark viewer): broadcast_spatial_notification (TTS at x/y/z via edge-tts), broadcast_spatial_audio (looping mp3/wav URL), place_world_tv (16:9 video plane), spawn_agent_avatar (default_agent = built-in GLB).

Meta: refine_with_local_llm (needs Ollama at OLLAMA_URL), generate_world_prompt (sampling-first expansion), worldlabs_help (detail quick/standard/verbose, topic generate/upload/poll/world/ spatial/meta), gallery_explore (see workflow 2), worldlabs_shutdown.

Read the full file on GitHub · 123 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 23d ago First seen · 123 lines · 43 tokens per session scan A 2cdfc31efc01

Subscribe to this mod's changes

worldlabs is a skill published in the GitHub repository sandraschi/worldlabs-mcp (24 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,592 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.

Creative and mediamarblemcp-serverwebappworldlabs
Related

worldlabs compared with skills from other repositories

worldlabs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
worldlabssandraschi/worldlabs-mcpSkill24todayMITA43Claude Code
blender-expertsandraschi/blender-mcpSkill658d agoMITA34Claude Code
autonomous-modelingsandraschi/blender-mcpSkill658d agoMITA36Claude Code
pipeline-automationsandraschi/blender-mcpSkill658d agoMITA29Claude Code
freecad-expertsandraschi/freecad-mcpSkill337d agoMITA0Claude Code
virtualization-expertsandraschi/virtualization-mcpSkill19todayMITA24Claude Code
qcad-cadsandraschi/qcad-mcpSkill18todayMITA41Claude Code