brick_get_scene
Returns the current scene state with all placed bricks and their footprints. Call this ONCE at the start of a building task — between your own brick_place calls, use the footprints in results instead.
This record as markdown: /tools/dend-brick-mcp-app/brick-get-scene.md
What brick_get_scene does on Brick Builder MCP App
AI agents call brick_get_scene to retrieve information from Brick Builder MCP App without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why brick_get_scene is rated Low
This tool performs a read-only query operation to fetch the state of a 3D scene. It retrieves information for inspection and planning purposes before placing new bricks. No data is created, modified, deleted, or executed. The lowest severity applies because misuse of a query tool poses minimal risk—an agent reading scene state multiple times has no harmful consequences.
From the tool's definition Tool returns the current scene state with all placed bricks and their footprints. The description explicitly states it retrieves data ('Returns the current scene state') with no indication of modifications, deletions, or side effects.
Attacks that exploit this kind of access
The rule that runs brick_get_scene safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Brick Builder MCP App, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For brick_get_scene, this is the rule to start with:
brick_get_scene is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Brick Builder MCP App, apply this rule, and every brick_get_scene call is checked against it from then on.
Questions about brick_get_scene
Returns the current scene state with all placed bricks and their footprints. Call this ONCE at the start of a building task — between your own brick_place calls, use the footprints in results instead. It is categorised as a Read tool in the Brick Builder MCP App MCP Server, which means it retrieves data without modifying state.
Register the Brick Builder MCP App MCP server in PolicyLayer and add a rule for brick_get_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 Brick Builder MCP App. Nothing to install.
brick_get_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 brick_get_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 brick_get_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.
brick_get_scene is provided by the Brick Builder MCP App MCP server (dend/brick-mcp-app). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Brick Builder MCP App, and thousands of servers like it.
This server
Across the catalogue