AI agents call redux_dispatch_action to retrieve information from Redux without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though redux_dispatch_action only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Dispatch an action to the Redux store. It is categorised as a Read tool in the Redux MCP Server, which means it retrieves data without modifying state.
Register the Redux MCP server in PolicyLayer and add a rule for redux_dispatch_action: 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_dispatch_action 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 redux_dispatch_action 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_dispatch_action. 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_dispatch_action 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 →