// MCP TOOL REFERENCE

WORLDLABS TOOLS

20 tools from the Worldlabs MCP Server, categorised by risk level.

View the Worldlabs policy →
// ALL 20 WORLDLABS TOOLS
READ 5 tools
Read get_operation get_operation Read get_world Fetch the latest details for a generated world by its ID. Read list_worlds List previously generated worlds. Read show_world_card show_world_card Read show_worlds_card show_worlds_card
WRITE 5 tools
Write broadcast_spatial_notification broadcast_spatial_notification Write place_world_tv Place a virtual TV screen in the 3D world playing a Veo 3.1 video. Write prepare_media_upload prepare_media_upload Write spawn_agent_avatar Materialize an animated agent avatar in the 3D scene. Write upload_and_generate upload_and_generate
DESTRUCTIVE 1 tools
Destructive delete_world delete_world
EXECUTE 7 tools
Execute wait_for_world wait_for_world Execute broadcast_spatial_audio Broadcast spatial audio (Music/Ambience) to the scene. Execute generate_world_from_image generate_world_from_image Execute generate_world_from_media_asset generate_world_from_media_asset Execute generate_world_from_multi_image generate_world_from_multi_image Execute generate_world_from_text generate_world_from_text Execute generate_world_from_video generate_world_from_video
OTHER 2 tools
Other refine_with_local_llm refine_with_local_llm Other worldlabs_help worldlabs_help

Route Worldlabs through PolicyLayer and every one of its 20 tools is checked against your policy before it runs.

CHECK YOUR STACK →

See every tool, the dangerous ones, and the token cost across your stack.

// FAQ
How many tools does the Worldlabs MCP server have? +

The Worldlabs MCP server exposes 20 tools across 5 categories: Read, Write, Destructive, Execute, Other.

How do I enforce policies on Worldlabs tools? +

Route the Worldlabs server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Worldlabs tools fall into? +

Worldlabs tools are categorised as Read (5), Write (5), Destructive (1), Execute (7), Other (2). Each category has a recommended default policy.

Enforce policy on every Worldlabs tool call.

Start from Worldlabs, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.