AI agents call lexq_rules_get 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 tool retrieves and queries existing rule configurations without modifying, creating, deleting, or executing any business logic. It is a read-only operation that returns data for inspection or analysis. No destructive, financial, or executable actions are performed.
From the tool's definition Tool name 'lexq_rules_get' and description 'Get full rule detail including condition tree and action definitions' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get full rule detail including condition tree and action definitions. 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_rules_get: 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_rules_get 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_rules_get 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_rules_get. 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_rules_get 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.
lexq_rules_get is one line of LexQ'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 →