AI agents call search_contacts to retrieve information from Whatsapp 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 based on search criteria. It performs no writes, deletions, code execution, or financial transactions. The blast radius of misuse is minimal—an AI agent could retrieve contact details but cannot modify, delete, or act upon them. Classification as Read is appropriate.
From the tool's definition Tool description states 'Substring-search contacts by name, push name, or phone number' — a pure query operation with no modification or side effects. Server description emphasizes 'read-only interface to WhatsApp'.
Attacks that exploit this kind of access
Substring-search contacts by name, push name, or phone number. It is categorised as a Read tool in the Whatsapp MCP Server, which means it retrieves data without modifying state.
Register the Whatsapp MCP server in PolicyLayer and add a rule for search_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 Whatsapp. Nothing to install.
search_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 search_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 search_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.
search_contacts is provided by the Whatsapp MCP server (joaohts/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 →