AI agents call lexq_history_stats to retrieve information from LexQ without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries historical statistics and performance metrics. No data is created, modified, deleted, or executed. The tool has minimal blast radius if misused by an AI agent, as it only exposes performance telemetry.
From the tool's definition Tool retrieves execution KPIs including 'total executions, success/failure counts, success rate, and average latency'—purely diagnostic metrics with no modification or side effects.
Attacks that exploit this kind of access
Get execution KPIs: total executions, success/failure counts, success rate, and average latency. It is categorised as a Read tool in the LexQ MCP Server, which means it retrieves data without modifying state.
Register the LexQ MCP server in PolicyLayer and add a rule for lexq_history_stats: 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 LexQ. Nothing to install.
lexq_history_stats 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 lexq_history_stats 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 lexq_history_stats. 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.
lexq_history_stats is provided by the LexQ MCP server (lexq-io/lexq-cli). 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 →