delete_assistant
AI agents call delete_assistant to permanently remove resources in RunWhen Platform MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The 'delete_' prefix combined with 'assistant' as the object indicates this tool permanently removes an assistant entity from the RunWhen platform. Deletion is irreversible and represents data loss. While the empty description reduces confidence slightly, the clear naming pattern and presence of other delete operations on this server strongly suggest destructive capability.
From the tool's definition Tool name is 'delete_assistant' which indicates irreversible deletion. The description is empty, but the naming convention combined with the sibling context (delete_slx, delete_knowledge_base_article also present) establishes this as a destructive operation.
Attacks that exploit this kind of access
delete_assistant. It is categorised as a Destructive tool in the RunWhen Platform MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RunWhen Platform MCP server in PolicyLayer and add a rule for delete_assistant: 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 RunWhen Platform MCP. Nothing to install.
delete_assistant 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_assistant 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_assistant. 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_assistant is provided by the RunWhen Platform MCP server (runwhen-contrib/runwhen-platform-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 →