purge_memory
AI agents call purge_memory to permanently remove resources in Chronos MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs irreversible data deletion on the server's persistent memory system. Even without a detailed description, the name 'purge_memory' combined with the server's role as a persistent knowledge/memory store leaves no ambiguity—this is a destructive operation. A misused purge could permanently erase critical project state, task history, and decisions, making it high severity.
From the tool's definition Tool name is 'purge_memory' which explicitly indicates irreversible deletion of memory data. The verb 'purge' means to remove completely and permanently.
Attacks that exploit this kind of access
purge_memory. It is categorised as a Destructive tool in the Chronos MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Chronos MCP server in PolicyLayer and add a rule for purge_memory: 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 Chronos MCP. Nothing to install.
purge_memory 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 purge_memory 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 purge_memory. 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.
purge_memory is provided by the Chronos MCP server (kodaxadev/chronosmcp). 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 →