AI agents call clear_chat_history to permanently remove resources in Grok MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes chat history data without the ability to recover it. While the description is empty, the name explicitly indicates a destructive operation. The severity is high because loss of chat history could impact audit trails, user records, and data integrity, though the blast radius is somewhat limited to the chat context rather than critical system data or financial transactions.
From the tool's definition Tool name is 'clear_chat_history', which indicates irreversible deletion of historical data. The verb 'clear' combined with 'history' implies permanent removal of records.
Documented attack patterns abuse exactly the kind of access clear_chat_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Grok MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_chat_history:
{
"version": "1",
"default": "deny",
"hide": [
"clear_chat_history"
]
}clear_chat_history disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
clear_chat_history. It is categorised as a Destructive tool in the Grok MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Grok MCP server in PolicyLayer and add a rule for clear_chat_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 Grok MCP. Nothing to install.
clear_chat_history is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_chat_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 clear_chat_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.
clear_chat_history is provided by the Grok MCP server (merterbak/grok-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Grok MCP, 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.
22 Grok MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.