Delete a link from a lab
AI agents call delete_link 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 network links from a lab environment without the ability to undo via the tool itself. While the blast radius is contained to a specific lab (not production infrastructure), the deletion of links can break network topology configurations and require manual reconfiguration. In a Cisco Modeling Labs context used for training or testing, this could corrupt lab scenarios.
From the tool's definition Tool name is 'delete_link' with description 'Delete a link from a lab'. The verb 'delete' combined with network topology context indicates irreversible removal of a network link configuration.
Attacks that exploit this kind of access
Delete a link from a lab. 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_link: 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_link 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_link 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_link. 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_link 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 →