Deletes a glossary from your Lara Translate account.
AI agents call delete_glossary to permanently remove resources in Lara — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of a glossary is a destructive action that cannot be undone and eliminates data. This falls under the Destructive category per the ruleset. Severity is high because losing a glossary could impact translation workflows and productivity, though it is scoped to a single glossary rather than affecting financial systems or multiple accounts.
From the tool's definition Tool name 'delete_glossary' and description states it 'Deletes a glossary' — this is an irreversible operation that permanently removes data from the user's Lara Translate account.
Attacks that exploit this kind of access
Deletes a glossary from your Lara Translate account. It is categorised as a Destructive tool in the Lara MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lara MCP server in PolicyLayer and add a rule for delete_glossary: 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 Lara. Nothing to install.
delete_glossary 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 delete_glossary 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 delete_glossary. 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.
delete_glossary is provided by the Lara MCP server (@translated/lara-mcp). 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 →