Query room items by type, position, triggers, text search, parent, or quest reference. Automatically pulls fresh room data from the server. Filters combine with AND logic — all specified conditions must match. Returns matching items with full data (position, scale, logic, etc.).
AI agents call query_room to retrieve information from Portals without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
ids | array | — | Match specific item IDs. |
near | object | — | Center point for spatial query (requires radius). |
quest | string | — | Quest name to search for in interactions. |
types | array | — | Match by prefabName, e.g. ['Trigger', 'GLB', 'ResizableCube']. |
parent | string | — | Parent item ID — returns children of this parent. |
radius | number | — | Radius for spatial query (requires near). |
roomId | string | — | Room ID. Falls back to PORTALS_ROOM_ID env variable if omitted. |
search | string | — | Case-insensitive text search across all string fields. |
hasEffects | boolean | — | If true, only items with at least one effect in any interaction. |
hasTriggers | boolean | — | If true, only items with at least one interaction trigger. |
Parameters from the server's own tool schema.
query_room is a pure data retrieval tool that filters and returns room inventory data based on search criteria (type, position, triggers, text, parent, quest reference). It reads and pulls fresh data from the server but does not create, modify, delete, or execute operations. The description contains no language indicating state changes, irreversible actions, code execution, or financial transactions.
From the tool's definition Tool description explicitly states it 'Query[s] room items' and 'Returns matching items with full data' — a retrieval operation with no modification or side effects.
Risk signalsHigh parameter count (13 properties)
Attacks that exploit this kind of access
Query room items by type, position, triggers, text search, parent, or quest reference. Automatically pulls fresh room data from the server. Filters combine with AND logic — all specified conditions must match. Returns matching items with full data (position, scale, logic, etc.). It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.
query_room accepts 10 parameters: ids, near, quest, types, parent, radius, roomId, search, hasEffects, hasTriggers. The full parameter table on this page comes from the server's own tool schema.
Register the Portals MCP server in PolicyLayer and add a rule for query_room: 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 Portals. Nothing to install.
query_room 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 query_room 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 query_room. 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.
query_room is provided by the Portals MCP server (portals-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →