AI agents call rms_order_detail to retrieve information from Rms without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing order details by order number. It is a read/fetch operation with no side effects, modifications, or destructive actions. The server description confirms it is for 'retrieval of Rakuten RMS sales data'.
From the tool's definition 'Full order detail by order number(s)' - retrieves order information, read-only query
Attacks that exploit this kind of access
Full order detail by order number(s). It is categorised as a Read tool in the Rms MCP Server, which means it retrieves data without modifying state.
Register the Rms MCP server in PolicyLayer and add a rule for rms_order_detail: 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 Rms. Nothing to install.
rms_order_detail 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 rms_order_detail 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 rms_order_detail. 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.
rms_order_detail is provided by the Rms MCP server (yasuhidekoizumi-afk/rms-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 →