bake_reflections
Bake all EnvmapProbe reflection probes in the scene (EnvmapProbe.BakeAll) so they actually capture their surroundings — placing a probe with add_envmap_probe does nothing visible until it
This record as markdown: /tools/sbox/bake-reflections.md
What bake_reflections does on Sbox
AI agents invoke bake_reflections to trigger actions in Sbox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why bake_reflections is rated High
This tool triggers an active rendering/computation operation (BakeAll) across the entire scene. It executes a baking process that generates and stores reflection data — this is an external operation with side effects beyond simple data retrieval or creation, akin to running a render job. It modifies scene assets (reflection probe data) as a result of execution, making Execute the most appropriate category.
From the tool's definition Bake all EnvmapProbe reflection probes in the scene (EnvmapProbe.BakeAll) so they actually capture their surroundings
Attacks that exploit this kind of access
The rule that runs bake_reflections safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sbox, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bake_reflections, this is the rule to start with:
bake_reflections stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every bake_reflections call is checked against it from then on.
Questions about bake_reflections
Bake all EnvmapProbe reflection probes in the scene (EnvmapProbe.BakeAll) so they actually capture their surroundings — placing a probe with add_envmap_probe does nothing visible until it. It is categorised as a Execute tool in the Sbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sbox MCP server in PolicyLayer and add a rule for bake_reflections: 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 Sbox. Nothing to install.
bake_reflections is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bake_reflections 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 bake_reflections. 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.
bake_reflections is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sbox, and thousands of servers like it.
This server
Across the catalogue