AI agents invoke wave_send_invoice to trigger actions in Waveapps. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external communication action — sending an invoice via email to recipients. It is not purely a write/data-modification operation; it executes an external operation (email delivery) with real-world effects that cannot be easily undone. Misuse could result in sending incorrect invoices to customers, causing confusion or financial disputes.
From the tool's definition 'Sends an approved invoice to one or more recipients via Wave'
Attacks that exploit this kind of access
Sends an approved invoice to one or more recipients via Wave\. It is categorised as a Execute tool in the Waveapps MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Waveapps MCP server in PolicyLayer and add a rule for wave_send_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_send_invoice is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the wave_send_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_send_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_send_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 →