Compare two room snapshots to see what changed — added/removed/moved/rescaled objects, zone changes, and stats comparison. Use after applying edits to verify improvements. Requires two snapshot file paths from get_room_data.
AI agents call compare_scene 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 |
|---|---|---|---|
focus | object | — | Optional focus to narrow the analysis scope. |
filePath | string | Yes | Path to the current (after) snapshot.json. |
beforeFilePath | string | Yes | Path to the previous (before) snapshot.json. |
Parameters from the server's own tool schema.
This is a read-only operation that queries and analyzes data from two existing snapshots to report differences. It has no side effects on data—it neither modifies, deletes, executes code, nor commits financial obligations. The purpose is verification and observation after other operations have already been applied.
From the tool's definition The tool compares snapshots and shows changes without modifying data: 'Compare two room snapshots to see what changed — added/removed/moved/rescaled objects, zone changes, and stats comparison.
Risk signalsAccepts file system path (filePath)
Attacks that exploit this kind of access
Compare two room snapshots to see what changed — added/removed/moved/rescaled objects, zone changes, and stats comparison. Use after applying edits to verify improvements. Requires two snapshot file paths from get_room_data. It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.
compare_scene accepts 3 parameters: focus, filePath, beforeFilePath. Required: filePath, beforeFilePath. 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 compare_scene: 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.
compare_scene 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 compare_scene 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 compare_scene. 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.
compare_scene 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 →