AI agents use whatsapp_send_text to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
to | string | Yes | Recipient phone number in E.164 format |
body | string | Yes | Message text |
preview_url | boolean | — | |
bearer_token | string | Yes | |
phone_number_id | string | Yes | Your WhatsApp phone number ID from Meta for Developers |
Parameters from the server's own tool schema.
This tool creates and sends data (a text message) via a real messaging service. While messages are not stored data reversals, they represent irreversible communications sent to external parties. Misuse by an AI agent could result in spam, phishing, social engineering, or harassment campaigns. The high severity reflects the potential blast radius: mass unsolicited messaging, impersonation, or credential theft.
From the tool's definition Tool name 'whatsapp_send_text' and description 'Send a text message via WhatsApp Business Cloud API' indicate creation and transmission of a message to an external recipient.
Risk signalsAccepts raw HTML/template content (body)
Attacks that exploit this kind of access
Send a text message via WhatsApp Business Cloud API. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
whatsapp_send_text accepts 5 parameters: to, body, preview_url, bearer_token, phone_number_id. Required: to, body, bearer_token, phone_number_id. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for whatsapp_send_text: 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 UnClick. Nothing to install.
whatsapp_send_text 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 whatsapp_send_text 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 whatsapp_send_text. 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.
whatsapp_send_text is provided by the UnClick MCP server (@unclick/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 →