AI agents invoke send_flow_message to trigger actions in Whatsapp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool sends an interactive flow/form message to an external user via WhatsApp, triggering an external communication operation. It is not a simple data write — it executes an outbound message delivery to a real user, potentially at scale. Misuse could result in spamming users with unwanted interactive forms.
From the tool's definition Send a WhatsApp Flow to a user. The user sees an interactive form/survey directly in the chat.
Attacks that exploit this kind of access
Send a WhatsApp Flow to a user. The user sees an interactive form/survey directly in the chat. It is categorised as a Execute tool in the Whatsapp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Whatsapp MCP server in PolicyLayer and add a rule for send_flow_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 Whatsapp. Nothing to install.
send_flow_message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send_flow_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_flow_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_flow_message 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 →