Email an invoice to one or more recipients
AI agents use send_invoice to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
Sending an invoice is a Write action: it creates and transmits a document to recipients. While it operates in a financial context (AP2 payment protocol), the tool itself does not execute a payment or commit a financial obligation — it only communicates invoice information.
From the tool's definition 'Email an invoice to one or more recipients' — sending an email with invoice content creates/transmits a document but does not itself move money or irrevocably delete data
Documented attack patterns abuse exactly the kind of access send_invoice gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for send_invoice:
{
"version": "1",
"default": "deny",
"tools": {
"send_invoice": {
"limits": [
{
"counter": "send_invoice_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_invoice stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Email an invoice to one or more recipients. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for 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 Mcp Ap2. Nothing to install.
send_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 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 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.
send_invoice is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.