Get all chats
AI agents call get_chats to retrieve information from Evolution API WhatsApp MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves chat data from WhatsApp without creating, modifying, deleting, or executing any operations. It has no destructive capability and poses minimal risk—the primary concern would be unauthorized access to chat information, which is an access control issue rather than a tool severity issue. Blast radius is limited to information disclosure.
From the tool's definition Tool name 'get_chats' and description 'Get all chats' indicates a retrieval operation with no modification. The verb 'get' is explicitly listed in the Read category rules as a non-side-effects operation.
Attacks that exploit this kind of access
Get all chats. It is categorised as a Read tool in the Evolution API WhatsApp MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Evolution API WhatsApp MCP Server MCP server in PolicyLayer and add a rule for get_chats: 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 Evolution API WhatsApp MCP Server. Nothing to install.
get_chats 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_chats 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_chats. 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_chats is provided by the Evolution API WhatsApp MCP Server MCP server (luiso2/mcp-evolution-api). 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 →