List draft bills (ACCPAY invoices) - use to find existing draft to add expenses to
AI agents call xero_list_draft_bills to retrieve information from Xero Expenses MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns draft bill data from Xero without creating, modifying, deleting, or executing any operations. It is a passive read operation used to enumerate existing records, fitting the Read category.
From the tool's definition Tool name contains 'list' and description states 'List draft bills' with purpose to 'find existing draft' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
List draft bills (ACCPAY invoices) - use to find existing draft to add expenses to. It is categorised as a Read tool in the Xero Expenses MCP MCP Server, which means it retrieves data without modifying state.
Register the Xero Expenses MCP server in PolicyLayer and add a rule for xero_list_draft_bills: 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 Xero Expenses MCP. Nothing to install.
xero_list_draft_bills 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 xero_list_draft_bills 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 xero_list_draft_bills. 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.
xero_list_draft_bills is provided by the Xero Expenses MCP server (muness/xero-expenses-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 →