AI agents call inspect_rule to retrieve information from Run Iq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
inspect_rule retrieves and examines rule properties and metadata without creating, modifying, or deleting any data. It is a read-only introspection operation with no side effects. Even in a policy engine context, inspection of rule parameters poses minimal risk—the tool does not execute policies, modify configurations, or trigger external operations.
From the tool's definition Tool performs analysis and inspection of a rule without modification: 'Analyze a single Run-IQ rule in detail: checksum, model, active dates, params, and plugin-specific fields.' Returns metadata about existing rules.
Attacks that exploit this kind of access
Analyze a single Run-IQ rule in detail: checksum, model, active dates, params, and plugin-specific fields. It is categorised as a Read tool in the Run Iq MCP Server, which means it retrieves data without modifying state.
Register the Run Iq MCP server in PolicyLayer and add a rule for inspect_rule: 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 Run Iq. Nothing to install.
inspect_rule 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 inspect_rule 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 inspect_rule. 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.
inspect_rule is provided by the Run Iq MCP server (run-iq/mcp-server). 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 →