Delete one business glossary term by its id.
AI agents call delete_glossary_term to permanently remove resources in Querywise — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes metadata (a glossary term) from the semantic layer. While not as critical as deleting production data, deletion of business glossary terms is destructive and cannot be undone—it would break semantic understanding and documentation for users relying on that term.
From the tool's definition Tool name is 'delete_glossary_term' and description states 'Delete one business glossary term by its id.' The verb 'delete' combined with the action of removing a glossary term indicates irreversible data deletion.
Attacks that exploit this kind of access
Delete one business glossary term by its id. It is categorised as a Destructive tool in the Querywise MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Querywise MCP server in PolicyLayer and add a rule for delete_glossary_term: 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 Querywise. Nothing to install.
delete_glossary_term 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_term 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_term. 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_term is provided by the Querywise MCP server (kosminus/querywise-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 →