AI agents use whatsapp_import_chat to create or update resources in Waha — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Waha environment.
The tool imports historical messages into a message store, which is a write/create operation that adds data. While it modifies the stored state, the operation is reversible (imported data can be removed or re-imported) and does not constitute irreversible deletion (Destructive), code execution (Execute), or financial transaction (Financial).
From the tool's definition Tool performs 'Import a WhatsApp chat export file... into the message store' - this creates/adds records reversibly to a data store without deletion or external financial impact.
Attacks that exploit this kind of access
Import a WhatsApp chat export file (ZIP or TXT) into the message store. Use this to backfill historical messages from WhatsApp. It is categorised as a Write tool in the Waha MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Waha MCP server in PolicyLayer and add a rule for whatsapp_import_chat: 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 Waha. Nothing to install.
whatsapp_import_chat 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_import_chat 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_import_chat. 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_import_chat is provided by the Waha MCP server (@marcos-heidemann/waha-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 →