describe_project
One-call project orientation: identity (name/ident/org/type), the open scene with object count, scene and prefab file lists (capped at 50 each, Libraries/.sbox excluded), code footprint (.cs/.razor counts), custom Component types (up to 100, engine types excluded), and installed libraries. Return...
This record as markdown: /tools/sbox/describe-project.md
What describe_project does on Sbox
AI agents call describe_project to retrieve information from Sbox without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why describe_project is rated Low
Tool retrieves project metadata and file lists without modifying or executing code.
From the tool's definition describe_project returns structured summary, read-only, no side effects
Attacks that exploit this kind of access
The rule that runs describe_project 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 describe_project, this is the rule to start with:
describe_project 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 Sbox, apply this rule, and every describe_project call is checked against it from then on.
Questions about describe_project
One-call project orientation: identity (name/ident/org/type), the open scene with object count, scene and prefab file lists (capped at 50 each, Libraries/.sbox excluded), code footprint (.cs/.razor counts), custom Component types (up to 100, engine types excluded), and installed libraries. Returns a structured summary — orient here first, then get_scene_hierarchy for the scene, describe_type for components, find_broken_references for project health. Read-only. It is categorised as a Read tool in the Sbox MCP Server, which means it retrieves data without modifying state.
Register the Sbox MCP server in PolicyLayer and add a rule for describe_project: 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.
describe_project 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 describe_project 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 describe_project. 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.
describe_project 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