Delete a model.
AI agents call delete_model_tool to permanently remove resources in Qiskit Gym MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs deletion, which is an irreversible action that cannot be undone. This places it in the Destructive category. Severity is high because deletion of ML models trained in a reinforcement learning context could represent significant loss of computational work and trained state, though the blast radius is limited to the specific model artifact rather than system-wide data.
From the tool's definition Tool name 'delete_model_tool' and description 'Delete a model' indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete a model. It is categorised as a Destructive tool in the Qiskit Gym MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qiskit Gym MCP Server MCP server in PolicyLayer and add a rule for delete_model_tool: 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 Qiskit Gym MCP Server. Nothing to install.
delete_model_tool 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_model_tool 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_model_tool. 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_model_tool is provided by the Qiskit Gym MCP Server MCP server (qiskit-gym-mcp-server). 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 →