Read back any persisted request (sync or async) from the flight recorder by correlationId, including prompt and response.
AI agents call llm_request_result to retrieve information from LLM CLI Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical LLM requests and responses by correlationId. While it is fundamentally a Read operation, the severity is elevated to 'medium' because it may expose sensitive data (prompts, responses, and potentially secrets or credentials) that were sent to or received from LLM services, depending on what was logged in the flight recorder.
From the tool's definition Tool name 'llm_request_result' and description 'Read back any persisted request... from the flight recorder' clearly indicate retrieval of stored data with no modification or execution.
Documented attack patterns abuse exactly the kind of access llm_request_result gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LLM CLI Gateway, and nothing reaches the server without passing your rules. This is the rule we recommend for llm_request_result:
{
"version": "1",
"default": "deny",
"tools": {
"llm_request_result": {}
}
}llm_request_result is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read back any persisted request (sync or async) from the flight recorder by correlationId, including prompt and response. It is categorised as a Read tool in the LLM CLI Gateway MCP Server, which means it retrieves data without modifying state.
Register the LLM CLI Gateway MCP server in PolicyLayer and add a rule for llm_request_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 LLM CLI Gateway. Nothing to install.
llm_request_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 llm_request_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 llm_request_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.
llm_request_result is provided by the LLM CLI Gateway MCP server (llm-cli-gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LLM CLI Gateway, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
46 LLM CLI Gateway tools catalogued and risk-classified — across an index of 43,000+ MCP servers.