AI agents use send_cta_url_button to create or update resources in Whatsapp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Whatsapp environment.
This tool sends a message, which is a create operation (Write category). It does not execute arbitrary code, delete data, move money, or cause irreversible harm. However, severity is elevated to 'medium' because sending messages at scale or to unintended recipients via an AI agent could enable spam, phishing, or social engineering attacks on WhatsApp users.
From the tool's definition Tool name 'send_cta_url_button' and description 'Send a message with a call-to-action URL button' indicate the tool creates and transmits a new message—a reversible write operation.
Attacks that exploit this kind of access
Send a message with a call-to-action URL button. It is categorised as a Write tool in the Whatsapp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Whatsapp MCP server in PolicyLayer and add a rule for send_cta_url_button: 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. Nothing to install.
send_cta_url_button 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_cta_url_button 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_cta_url_button. 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_cta_url_button is provided by the Whatsapp MCP server (spirit122/whatsapp-mcp-server). 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 →