WHEN TO USE: To remove a specific prompt from a project.
AI agents call lbm_delete_prompt to permanently remove resources in LLM Brand Monitor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion of a prompt, fitting the Destructive category definition ('irreversibly deletes or overwrites data'). While the blast radius is somewhat limited to individual prompts within a monitoring project (not system-wide data destruction), unauthorized deletion of project prompts could disrupt brand monitoring workflows and erase historical configuration.
From the tool's definition Tool name contains 'delete' and description states 'To remove a specific prompt from a project' — a deletion operation that is irreversible.
Attacks that exploit this kind of access
WHEN TO USE: To remove a specific prompt from a project. It is categorised as a Destructive tool in the LLM Brand Monitor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LLM Brand Monitor MCP server in PolicyLayer and add a rule for lbm_delete_prompt: 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 LLM Brand Monitor. Nothing to install.
lbm_delete_prompt 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 lbm_delete_prompt 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 lbm_delete_prompt. 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.
lbm_delete_prompt is provided by the LLM Brand Monitor MCP server (@serpstat/llm-brand-monitor-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 →