Delete a stored entity by internal ID.
AI agents call state_delete to permanently remove resources in Onboarded MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on stored entities. Even though the blast radius depends on which entity is targeted and the agent's access controls, deletion cannot be undone and represents permanent data loss. This makes it Destructive rather than Write.
From the tool's definition Tool name is 'state_delete' and description explicitly states 'Delete a stored entity by internal ID' — the verb 'delete' combined with 'Delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a stored entity by internal ID. It is categorised as a Destructive tool in the Onboarded MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Onboarded MCP Server MCP server in PolicyLayer and add a rule for state_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 Onboarded MCP Server. Nothing to install.
state_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 state_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 state_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.
state_delete is provided by the Onboarded MCP Server MCP server (onboardedinc/onboarded-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 →