Reset Redux state and action history to initial values.
AI agents call redux_reset_state to permanently remove resources in Redux — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Resetting state and action history cannot be undone and destroys data (the action history and current state snapshot). While not a traditional delete operation, the irreversible loss of state and history qualifies as destructive.
From the tool's definition Tool description explicitly states 'Reset Redux state and action history to initial values' — this irreversibly clears both current state and historical action records.
Attacks that exploit this kind of access
Reset Redux state and action history to initial values. It is categorised as a Destructive tool in the Redux MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Redux MCP server in PolicyLayer and add a rule for redux_reset_state: 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 Redux. Nothing to install.
redux_reset_state 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 redux_reset_state 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 redux_reset_state. 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.
redux_reset_state is provided by the Redux MCP server (n1snt/redux-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 →