Run a combined group-membership audit (overlaps, no direct chat, not in contacts).
AI agents call run_group_audit to retrieve information from WhatsApp MCP Stream without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool runs an audit combining read-only checks (group overlaps, direct chat presence, contact membership). It retrieves and analyzes data without modifying, deleting, or sending anything. Severity is low as it only reads group/contact metadata, though there is slight uncertainty since 'audit' could theoretically trigger side effects not described.
From the tool's definition 'audit' and 'overlaps, no direct chat, not in contacts' — this is a read/analysis operation that queries group membership data and combines multiple read-type checks
Attacks that exploit this kind of access
Run a combined group-membership audit (overlaps, no direct chat, not in contacts). It is categorised as a Read tool in the WhatsApp MCP Stream MCP Server, which means it retrieves data without modifying state.
Register the WhatsApp MCP Stream MCP server in PolicyLayer and add a rule for run_group_audit: 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 MCP Stream. Nothing to install.
run_group_audit 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 run_group_audit 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 run_group_audit. 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.
run_group_audit is provided by the WhatsApp MCP Stream MCP server (loglux/whatsapp-mcp-stream). 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 →