AI agents use send_poll 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 a poll message is a reversible write operation—it creates new data (the poll message) in WhatsApp. It has no destructive effects, does not execute arbitrary code, does not move money, and does not permanently delete anything. While the tool appears incongruous with the AP2 payment protocol context of its server, its function is purely to create a communication artifact.
From the tool's definition Tool name is 'send_poll' and description states it 'Send[s] a poll message via WhatsApp'. This action creates and transmits a new message object (a poll) to a communication channel.
Documented attack patterns abuse exactly the kind of access send_poll 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_poll:
{
"version": "1",
"default": "deny",
"tools": {
"send_poll": {
"limits": [
{
"counter": "send_poll_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_poll 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 poll message via WhatsApp. 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_poll: 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_poll 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_poll 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_poll. 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_poll 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.