Delete a saved reasoning session by exact ID.
AI agents call deep_delete_session to permanently remove resources in Deep Reasoning — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a reasoning session record. Deletion cannot be undone and represents loss of data. While the blast radius is limited to reasoning sessions (not system-critical), the irreversible nature and lack of recovery mechanism classify it as Destructive rather than Write.
From the tool's definition Tool name explicitly states 'delete' and description says 'Delete a saved reasoning session by exact ID' — irreversible removal of stored data.
Attacks that exploit this kind of access
Delete a saved reasoning session by exact ID. It is categorised as a Destructive tool in the Deep Reasoning MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Deep Reasoning MCP server in PolicyLayer and add a rule for deep_delete_session: 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 Deep Reasoning. Nothing to install.
deep_delete_session 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 deep_delete_session 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 deep_delete_session. 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.
deep_delete_session is provided by the Deep Reasoning MCP server (mauriziomocci/deep-reasoning-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 →