AI agents call get_delivery_stats 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 only reads and aggregates historical analytics data about message delivery performance. It does not modify, delete, execute operations, or incur financial obligations. The worst-case misuse would be unauthorized access to business metrics, which has low blast radius compared to messaging or financial operations. Classified as Read with low severity.
From the tool's definition Tool retrieves message delivery statistics (sent, delivered, read, failed counts) within a date range. The description uses query language: 'get' and 'statistics', indicating data retrieval with no side effects.
Attacks that exploit this kind of access
Get message delivery statistics — how many messages were sent, delivered, read, and failed in a date range. 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 get_delivery_stats: 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.
get_delivery_stats 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 get_delivery_stats 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 get_delivery_stats. 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.
get_delivery_stats is provided by the Whatsapp MCP server (spirit122/whatsapp-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 →