List logged past policy evaluations (most recent first). Each row is one decision with its result and a single human-readable reason — NOT a live rule-by-rule trace. Shows how the JIT/policy engine has been deciding access.
AI agents call list_policy_evaluations to retrieve information from KVMFleet MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical policy evaluation records and audit data without creating, modifying, deleting, or executing any operations. It is consistent with the server's stated purpose as a 'read-only MCP server.' The blast radius of misuse is minimal—an agent could only access historical decision logs, which would not compromise system integrity or enable unauthorized actions.
From the tool's definition Tool description states it 'List logged past policy evaluations' and 'Shows how the JIT/policy engine has been deciding access.' The verb 'list' and focus on retrieving historical logged decisions with no modification capability indicates a read-only query…
Attacks that exploit this kind of access
List logged past policy evaluations (most recent first). Each row is one decision with its result and a single human-readable reason — NOT a live rule-by-rule trace. Shows how the JIT/policy engine has been deciding access. It is categorised as a Read tool in the KVMFleet MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KVMFleet MCP Server MCP server in PolicyLayer and add a rule for list_policy_evaluations: 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 KVMFleet MCP Server. Nothing to install.
list_policy_evaluations 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 list_policy_evaluations 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 list_policy_evaluations. 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.
list_policy_evaluations is provided by the KVMFleet MCP Server MCP server (kvmfleet/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_policy_evaluations is one line of KVMFleet MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →