Get world metadata from FoundryVTT. Returns information about the world such as title, system, version, and other metadata. This excludes document collections (actors, items, scenes, etc.) - use the specific get_* tools for those.
AI agents call get_world to retrieve information from FoundryMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_world only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Get world metadata from FoundryVTT. Returns information about the world such as title, system, version, and other metadata. This excludes document collections (actors, items, scenes, etc.) - use the specific get_* tools for those. It is categorised as a Read tool in the FoundryMCP MCP Server, which means it retrieves data without modifying state.
Register the Foundry MCP server in PolicyLayer and add a rule for get_world: 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 FoundryMCP. Nothing to install.
get_world 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 get_world 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 get_world. 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.
get_world is provided by the Foundry MCP server (thestranjer/foundry-vtt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.