Get messages from a specific WhatsApp chat. Returns message content, sender, timestamp, and status. Default limit is 10 messages.
AI agents call waha_get_messages to retrieve information from WAHA MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read operation that queries existing WhatsApp chat data without side effects. It neither modifies, deletes, nor executes operations. The severity is low because retrieving message history has limited blast radius—the risk is primarily informational exposure rather than operational impact. The high confidence reflects the clear read-only nature of the operation.
From the tool's definition Tool retrieves message content, sender, timestamp, and status with a default limit of 10 messages. The description uses 'Get messages' and 'Returns', indicating data retrieval with no modification or deletion.
Documented attack patterns abuse exactly the kind of access waha_get_messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WAHA MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for waha_get_messages:
{
"version": "1",
"default": "deny",
"tools": {
"waha_get_messages": {}
}
} waha_get_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get messages from a specific WhatsApp chat. Returns message content, sender, timestamp, and status. Default limit is 10 messages. It is categorised as a Read tool in the WAHA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WAHA MCP Server MCP server in PolicyLayer and add a rule for waha_get_messages: 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 WAHA MCP Server. Nothing to install.
waha_get_messages 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 waha_get_messages 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 waha_get_messages. 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.
waha_get_messages is provided by the WAHA MCP Server MCP server (seejux/waha-whatsapp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WAHA MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
52 WAHA MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.