Delete a question.
AI agents call blawx_question_delete to permanently remove resources in Blawx MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a question from the Blawx knowledge base, which cannot be undone. Deletion operations that destroy data irreversibly fall into the Destructive category. The high severity reflects that an agent deleting questions could corrupt or degrade the logical model and analysis capabilities, affecting downstream queries and fact scenarios that depend on those questions.
From the tool's definition Tool name 'blawx_question_delete' and description 'Delete a question' indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete a question. It is categorised as a Destructive tool in the Blawx MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Blawx MCP Server MCP server in PolicyLayer and add a rule for blawx_question_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 Blawx MCP Server. Nothing to install.
blawx_question_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 blawx_question_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 blawx_question_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.
blawx_question_delete is provided by the Blawx MCP Server MCP server (lexpedite/blawx_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 →