Delete a lab from CML
AI agents call delete_lab to permanently remove resources in Claude-Modeling-Labs MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a lab from Cisco Modeling Labs, destroying all associated configuration, topology, and state data. Deletion cannot be undone without restore from backup. While the blast radius is limited to a single lab (not system-wide or financial), the irreversible nature of data destruction and potential loss of work justifies the Destructive category and high severity.
From the tool's definition Tool name is 'delete_lab' and description states 'Delete a lab from CML' — the verb 'delete' indicates irreversible removal of data (an entire lab environment).
Attacks that exploit this kind of access
Delete a lab from CML. It is categorised as a Destructive tool in the Claude-Modeling-Labs MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude-Modeling-Labs MCP Server MCP server in PolicyLayer and add a rule for delete_lab: 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 Claude-Modeling-Labs MCP Server. Nothing to install.
delete_lab 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_lab 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_lab. 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_lab is provided by the Claude-Modeling-Labs MCP Server MCP server (mediocretriumph/claude-cml-toolkit). 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 →