AI agents call get_sys_helpers to retrieve information from Gobox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system metadata and reference information (enums, status codes) used for understanding the Gobox platform's available options. No data is created, modified, deleted, or any external operations triggered. It is purely informational and returns static reference material.
From the tool's definition Tool description states 'Fetch system enum/status reference' - a retrieval operation that queries reference data without modification. The term 'Fetch' and 'reference' indicate a read-only lookup of static system enumerations and status types.
Attacks that exploit this kind of access
Fetch system enum/status reference (order statuses, types, etc.). It is categorised as a Read tool in the Gobox MCP Server, which means it retrieves data without modifying state.
Register the Gobox MCP server in PolicyLayer and add a rule for get_sys_helpers: 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 Gobox. Nothing to install.
get_sys_helpers 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 get_sys_helpers 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 get_sys_helpers. 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.
get_sys_helpers is provided by the Gobox MCP server (winter279/gobox-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 →