update_invoice
AI agents use update_invoice to create or update resources in Cliniko MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cliniko MCP Server environment.
The tool modifies existing invoice data (reversible update operation), placing it in the Write category rather than Financial—financial transactions typically involve money movement or commitments, not invoice record updates. However, severity is high due to the healthcare/practice management context where invoice tampering could affect billing accuracy and patient accounts.
From the tool's definition Tool name 'update_invoice' indicates modification of invoice records. Server context shows Cliniko is a practice management system handling financial and patient data.
Attacks that exploit this kind of access
update_invoice. It is categorised as a Write tool in the Cliniko MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cliniko MCP Server MCP server in PolicyLayer and add a rule for update_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 Cliniko MCP Server. Nothing to install.
update_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 update_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 update_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.
update_invoice is provided by the Cliniko MCP Server MCP server (yasboop/new-cliniko-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 →