Search across all collections (actors, items, scenes, journals) by name
AI agents call search_world to retrieve information from FoundryVTT MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_world tool is a read-only operation that retrieves information from the FoundryVTT world without modifying any data. It queries existing collections to locate entities by name, similar to a search or filter function. There are no side effects, no code execution, no data modification, and no destructive operations.
From the tool's definition Tool description states 'Search across all collections (actors, items, scenes, journals) by name' - this is a query/search operation with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access search_world gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FoundryVTT MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_world:
{
"version": "1",
"default": "deny",
"tools": {
"search_world": {}
}
}search_world 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.
Search across all collections (actors, items, scenes, journals) by name. It is categorised as a Read tool in the FoundryVTT MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FoundryVTT MCP Server MCP server in PolicyLayer and add a rule for search_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 FoundryVTT MCP Server. Nothing to install.
search_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 search_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 search_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.
search_world is provided by the FoundryVTT MCP Server MCP server (laurigates/foundryvtt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FoundryVTT MCP Server, 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.
25 FoundryVTT MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.