Which policy engines are connected and whether demo mode is active.
AI agents call cluster_status to retrieve information from PolicyPulse MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about policy engine connections and demo mode state. It is purely informational with no side effects, no data modification, no code execution, and no financial impact. The read-only nature and limited blast radius (only reveals current system state) justify a 'low' severity classification.
From the tool's definition Tool name is 'cluster_status' and description states it checks 'which policy engines are connected and whether demo mode is active' — a query operation with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Which policy engines are connected and whether demo mode is active. It is categorised as a Read tool in the PolicyPulse MCP MCP Server, which means it retrieves data without modifying state.
Register the PolicyPulse MCP server in PolicyLayer and add a rule for cluster_status: 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 PolicyPulse MCP. Nothing to install.
cluster_status 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 cluster_status 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 cluster_status. 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.
cluster_status is provided by the PolicyPulse MCP server (raviteja-pegata/policy-pulse-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 →