AI agents call request_history 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 queries historical message data from WhatsApp servers without altering, creating, or deleting content. It is purely retrieving information. While it accesses conversation history, there are no side effects beyond populating local message storage. The requirement for an anchor message is a technical constraint, not a capability modifier.
From the tool's definition Tool retrieves older messages via 'Request older messages' and 'history sync'; description explicitly indicates data retrieval with no modification or deletion ('Results arrive asynchronously via history sync').
Attacks that exploit this kind of access
Request older messages for a group from WhatsApp servers. Needs at least one message already in store as anchor. Results arrive asynchronously via history sync. 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 request_history: 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.
request_history 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 request_history 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 request_history. 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.
request_history 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 →