AI agents call get_group_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 retrieves and summarizes existing group metadata and message patterns. It has no side effects, does not modify data, does not execute code or commands, and does not move money. The worst misuse would be information disclosure about group activity patterns, which is a low-severity confidentiality risk. Confidence is high because the description clearly indicates data retrieval only.
From the tool's definition Tool provides aggregate statistics: 'Message counts, top contributors, hourly/daily activity, media breakdown' — all read-only analytics derived from group data without modification, deletion, or external execution.
Attacks that exploit this kind of access
Message counts, top contributors, hourly/daily activity, media breakdown for a group. 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_group_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_group_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_group_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_group_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_group_stats is provided by the Whatsapp MCP server (kotevcode/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 →