AI agents call unread_summary 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 and queries data (unread chat summaries and counts) with no capability to modify, delete, or execute actions. It is a pure Read operation with low severity due to limited scope—it exposes only metadata about which chats have unread messages, not the actual message content, reducing the risk if an AI agent misuses it.
From the tool's definition Tool provides a 'summary' and 'counts' of unread chats, explicitly stating 'No message bodies.' This is a query operation that retrieves metadata about chat state without exposing content or enabling side effects.
Attacks that exploit this kind of access
Summary of chats with unread messages and counts. No message bodies. 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 unread_summary: 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.
unread_summary 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 unread_summary 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 unread_summary. 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.
unread_summary 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 →