AI agents call explain_result 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.
This tool takes the output of a previous evaluation and presents it in a more digestible format. It has no side effects, does not execute new policies or rules, does not delete or modify data, and does not move money or trigger external systems. The blast radius of misuse is minimal—an attacker could only receive verbose explanations of already-computed results, which poses negligible security risk.
From the tool's definition Tool generates explanations and summaries of existing evaluation results without modifying data, creating new resources, or triggering external operations.
Attacks that exploit this kind of access
Generate a human-readable explanation of an evaluation result. Summarizes the total value, applied rules with their contributions, skipped rules with reasons, and execution timing. 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 explain_result: 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.
explain_result 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 explain_result 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 explain_result. 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.
explain_result 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 →