Attach a file (PDF, image) to an existing Xero invoice
AI agents use xero_attach_file_to_invoice to create or update resources in Xero Expenses MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xero Expenses MCP environment.
Attaching a file to an invoice is a Write operation: it modifies existing data (the invoice record) by adding metadata/attachments, but the change is reversible (the file can be removed). This is less severe than Destructive (which cannot be undone) and does not execute arbitrary code or move money.
From the tool's definition Tool description states 'Attach a file (PDF, image) to an existing Xero invoice' — this modifies an invoice by adding a file attachment, a reversible operation.
Attacks that exploit this kind of access
Attach a file (PDF, image) to an existing Xero invoice. It is categorised as a Write tool in the Xero Expenses MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xero Expenses MCP server in PolicyLayer and add a rule for xero_attach_file_to_invoice: 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_attach_file_to_invoice is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the xero_attach_file_to_invoice 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_attach_file_to_invoice. 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_attach_file_to_invoice 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 →