AI agents call whatsapp_list_contacts to retrieve information from Waha without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact information from a WhatsApp account without modifying, deleting, or executing any actions. It is purely a data query operation. Severity is medium rather than low because contact lists can be sensitive personal information whose exposure could enable social engineering or privacy violations, though the direct blast radius from misuse is constrained compared to write/execute/destructive…
From the tool's definition Tool description states 'lists people you DM and groups you' — a retrieval operation with no modification or deletion. The name 'list_contacts' also confirms read-only behavior.
Attacks that exploit this kind of access
Unified address book — lists people you DM and groups you. It is categorised as a Read tool in the Waha MCP Server, which means it retrieves data without modifying state.
Register the Waha MCP server in PolicyLayer and add a rule for whatsapp_list_contacts: 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_list_contacts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the whatsapp_list_contacts 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_list_contacts. 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_list_contacts 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 →