AI agents use send_whatsapp 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.
This tool creates and sends messages, which is a reversible Write action. Severity is medium rather than low because in the context of an Agent-to-Agent Payment Protocol server, sending unsolicited or malformed WhatsApp messages could be used for phishing, fraud communication, or social engineering related to financial transactions.
From the tool's definition Tool name 'send_whatsapp' and description 'Send a WhatsApp message' indicate creation/transmission of communication data.
Documented attack patterns abuse exactly the kind of access send_whatsapp 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_whatsapp:
{
"version": "1",
"default": "deny",
"tools": {
"send_whatsapp": {
"limits": [
{
"counter": "send_whatsapp_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} send_whatsapp 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.
Send a WhatsApp message. 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_whatsapp: 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_whatsapp 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_whatsapp 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_whatsapp. 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_whatsapp 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.