AI agents call redux_get_actions 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.
This tool queries and returns information about available Redux actions and dispatch history without modifying state, creating side effects, or executing arbitrary code. It is a straightforward data retrieval operation with no destructive, financial, or execution capabilities. Low severity because reading action metadata poses minimal risk even if exposed to an AI agent.
From the tool's definition Tool description states 'Return available actions and optionally dispatched history' — purely retrieval with no side effects. Name contains 'get' and description uses 'Return', both indicating read-only access.
Attacks that exploit this kind of access
Return available actions and optionally dispatched history. 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_get_actions: 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_get_actions 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_get_actions 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_get_actions. 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_get_actions 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 →