AI agents use send_whatsapp_media to create or update resources in Chatkazi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chatkazi environment.
This tool performs a Write operation—it creates and sends messages to external recipients via WhatsApp. While the message itself cannot be 'unsent' in practice after delivery, the capability is fundamentally about message creation/transmission rather than data deletion.
From the tool's definition Tool is described as 'Send a media message' which creates and transmits data to WhatsApp recipients. The action is reversible (messages can be deleted by users), and it modifies external state by delivering content to another party's WhatsApp account.
Attacks that exploit this kind of access
Send a media message (image, video, audio, or document) to a recipient. It is categorised as a Write tool in the Chatkazi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chatkazi MCP server in PolicyLayer and add a rule for send_whatsapp_media: 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 Chatkazi. Nothing to install.
send_whatsapp_media 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_whatsapp_media 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_whatsapp_media. 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_whatsapp_media is provided by the Chatkazi MCP server (lxmwaniky/chatkazi-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 →