This record as markdown: /tools/sbox/name.md
What name does on Sbox
AI agents use name to create or update resources in Sbox, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sbox environment.
Why name is rated Medium
Without a description, confidence is reduced significantly. However, the context of game engine tools that add/configure objects suggests this creates or modifies data (Write category) rather than merely reading. It could plausibly set an object's name property. Assigned medium severity due to the reversible nature of naming operations in game engines, though actual impact depends on undocumented functionality.
From the tool's definition Tool named 'name' with empty description on s&box game engine server alongside tools like 'add_component_to_new_object' and 'add_envmap_probe'. The name alone suggests property assignment or naming, likely creating or modifying game object metadata.
Attacks that exploit this kind of access
The rule that runs name 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 name, this is the rule to start with:
name stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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 name call is checked against it from then on.
Questions about name
name is a write tool on the Sbox MCP server. It is categorised as a Write tool in the Sbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sbox MCP server in PolicyLayer and add a rule for name: 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.
name is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the name 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 name. 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.
name 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