Return a compact, model-friendly summary of Portals room data without dumping the full JSON. Prefer file_path from get_room_data for large rooms. Reports item counts/types, variables, trigger/action types, warnings, and schema issues.
AI agents call inspect_room_data 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 |
|---|---|---|---|
file_path | string | — | Absolute path to a room-data JSON file, preferably returned by get_room_data. |
room_data | object | — | Small room data object to inspect directly. Prefer file_path for large rooms. |
Parameters from the server's own tool schema.
inspect_room_data is a read-only operation that retrieves and summarizes existing room data. It produces no side effects, makes no changes to state, and executes no external operations. The tool explicitly references preferring file_path 'for large rooms' rather than dumping full data, indicating it is a query/analysis tool.
From the tool's definition Tool description: 'Return a compact, model-friendly summary of Portals room data' and 'Reports item counts/types, variables, trigger/action types, warnings, and schema issues.' The verb 'Return' and 'Reports' indicate data retrieval only.
Risk signalsAccepts file system path (file_path)
Attacks that exploit this kind of access
Return a compact, model-friendly summary of Portals room data without dumping the full JSON. Prefer file_path from get_room_data for large rooms. Reports item counts/types, variables, trigger/action types, warnings, and schema issues. It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.
inspect_room_data accepts 2 parameters: file_path, room_data. 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 inspect_room_data: 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.
inspect_room_data 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 inspect_room_data 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 inspect_room_data. 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.
inspect_room_data 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 →