AI agents use send_template_message to create or update resources in Wati — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wati environment.
Sending template messages is a Write operation—it creates new message records and modifies conversation state in WATI's system, but is reversible (messages can be deleted/retracted). It has medium severity because widespread misuse could spam contacts or disrupt communications, but lacks the financial impact of a payment tool or irreversibility of deletion.
From the tool's definition Tool name 'send_template_message' and sibling tools like 'send_message_to_opened_session' and 'send_template_messages' indicate this sends WhatsApp messages. The server description states it enables 'send messages'.
Attacks that exploit this kind of access
send_template_message. It is categorised as a Write tool in the Wati MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wati MCP server in PolicyLayer and add a rule for send_template_message: 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 Wati. Nothing to install.
send_template_message 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_template_message 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_template_message. 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_template_message is provided by the Wati MCP server (jairajmehra/wati_whatsapp_mcp). 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 →