Analyze the spatial composition of a room — zones, relationships, design checks, and LLM reasoning templates. Requires get_room_data first to obtain the snapshot file path. Returns a text description, design check results (density, accessibility, scale, variety), and analysis templates. Use this ...
AI agents call analyze_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 snapshot.json from get_room_data. |
Parameters from the server's own tool schema.
This tool queries and retrieves spatial analysis data about a room's composition, zones, and design metrics. It has no side effects—it only provides information to inform subsequent decisions. The requirement to call get_room_data first and the emphasis on understanding state before changes confirms this is a reconnaissance/query operation, not a write, execute, or destructive action.
From the tool's definition analyze_scene returns 'a text description, design check results... and analysis templates' with no mention of modifying, deleting, or executing operations on the room.
Risk signalsAccepts file system path (filePath)
Attacks that exploit this kind of access
Analyze the spatial composition of a room — zones, relationships, design checks, and LLM reasoning templates. Requires get_room_data first to obtain the snapshot file path. Returns a text description, design check results (density, accessibility, scale, variety), and analysis templates. Use this before making composition changes to understand the current state. It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.
analyze_scene accepts 2 parameters: focus, filePath. Required: filePath. 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 analyze_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.
analyze_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 analyze_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 analyze_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.
analyze_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 →