Get full details for a draft order.
AI agents call get_draft_order to retrieve information from AdminAgent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data about a draft order without side effects. It does not create, modify, delete, or execute operations. Despite being part of an admin system with other sensitive tools (payments, discounts, inventory), this specific tool is purely informational and presents minimal risk if misused by an AI agent.
From the tool's definition Tool name is 'get_draft_order' and description states 'Get full details for a draft order' — the verb 'Get' indicates retrieval only, with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get full details for a draft order. It is categorised as a Read tool in the AdminAgent MCP Server, which means it retrieves data without modifying state.
Register the AdminAgent MCP server in PolicyLayer and add a rule for get_draft_order: 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 AdminAgent. Nothing to install.
get_draft_order 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_draft_order 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_draft_order. 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_draft_order is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →