Delete a DRAFT version. Only DRAFT versions can be deleted.
AI agents call lexq_versions_delete to permanently remove resources in LexQ — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes data (a DRAFT version) with no undo capability. Although restricted to DRAFT versions (which may be less critical than live versions), deletion is an irreversible destructive action. In a business rules management context, losing a DRAFT version could mean losing work, configurations, or policy iterations.
From the tool's definition Tool name contains 'delete' and description explicitly states 'Delete a DRAFT version'. The action irreversibly removes a version object.
Attacks that exploit this kind of access
Delete a DRAFT version. Only DRAFT versions can be deleted. It is categorised as a Destructive tool in the LexQ MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LexQ MCP server in PolicyLayer and add a rule for lexq_versions_delete: 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_versions_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the lexq_versions_delete 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_versions_delete. 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_versions_delete 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 →