AI agents use wave_update_invoice to create or update resources in Waveapps — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Waveapps environment.
This tool creates or modifies invoice data reversibly—a core Write category action. It is not Destructive (no deletion/irreversible action), not Execute (no code execution), and not Financial (does not move money or commit new obligations; it updates existing invoice state).
From the tool's definition Tool name 'wave_update_invoice' and description 'Patches an invoice via REST' indicates modification of existing financial documents. The verb 'patches' (HTTP PATCH) means partial update, which is reversible and modifies data without deletion.
Attacks that exploit this kind of access
Patches an invoice via REST. It is categorised as a Write tool in the Waveapps MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Waveapps MCP server in PolicyLayer and add a rule for wave_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 Waveapps. Nothing to install.
wave_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 wave_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 wave_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.
wave_update_invoice is provided by the Waveapps MCP server (lunaparker/waveapps-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 →