AI agents use lexq_groups_update to create or update resources in LexQ — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LexQ environment.
This tool creates or modifies data reversibly by updating policy group configurations. While not destructive (changes can be reverted), it directly alters business rule definitions that could impact system behavior, compliance, and operations if misused by an AI agent. The partial-update semantics (only provided fields changed) reduces risk slightly but does not lower it below Write.
From the tool's definition lexq_groups_update: 'Update a policy group. Only provided fields are updated; omitted fields remain unchanged.' The tool modifies existing policy group configurations, which are business rules that govern system behavior.
Attacks that exploit this kind of access
Update a policy group. Only provided fields are updated; omitted fields remain unchanged. It is categorised as a Write tool in the LexQ MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LexQ MCP server in PolicyLayer and add a rule for lexq_groups_update: 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_groups_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the lexq_groups_update 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_groups_update. 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_groups_update 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 →