Close a poll so no more votes can be cast
AI agents use close_poll to create or update resources in WhatsApp MCP Automation — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your WhatsApp MCP Automation environment.
Closing a poll modifies the poll object's state but does not delete data or trigger irreversible actions. It is reversible (a poll can be reopened in most systems). This qualifies as Write rather than Execute because it modifies a specific data object rather than running arbitrary code.
From the tool's definition Tool name 'close_poll' and description 'Close a poll so no more votes can be cast' indicate modification of poll state. This changes the poll's status from open to closed, preventing further voting—a reversible data modification.
Attacks that exploit this kind of access
Close a poll so no more votes can be cast. It is categorised as a Write tool in the WhatsApp MCP Automation MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the WhatsApp MCP Automation MCP server in PolicyLayer and add a rule for close_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 WhatsApp MCP Automation. Nothing to install.
close_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 close_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 close_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.
close_poll is provided by the WhatsApp MCP Automation MCP server (priyasogani8-star/whatsapp-mcp-automation). 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 →