AI agents call show_world_card to retrieve information from Worldlabs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the name 'show_world_card', this appears to be a read/display operation that retrieves and presents data about a generated world without modifying or deleting it. The sibling tools include write operations (generate_world_*), destructive operations (delete_world), and notification broadcasts, but this tool's name suggests only retrieval/display of existing world data.
From the tool's definition Tool name 'show_world_card' suggests displaying or retrieving a card representation of a world object. No destructive, financial, or code-execution keywords present. Lacks description, limiting confidence.
Documented attack patterns abuse exactly the kind of access show_world_card gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Worldlabs, and nothing reaches the server without passing your rules. This is the rule we recommend for show_world_card:
{
"version": "1",
"default": "deny",
"tools": {
"show_world_card": {}
}
}show_world_card is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
show_world_card. It is categorised as a Read tool in the Worldlabs MCP Server, which means it retrieves data without modifying state.
Register the Worldlabs MCP server in PolicyLayer and add a rule for show_world_card: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Worldlabs. Nothing to install.
show_world_card is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the show_world_card rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for show_world_card. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
show_world_card is provided by the Worldlabs MCP server (sandraschi/worldlabs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Worldlabs, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 Worldlabs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.