create_switch
AI agents use create_switch to create or update resources in Claude-Modeling-Labs MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude-Modeling-Labs MCP Server environment.
This tool creates a new network switch device within a CML lab environment. Creation is a Write operation—it adds a reversible component to the topology that can be deleted or modified. It has no financial impact and is not destructive (the action is undoable).
From the tool's definition Tool name 'create_switch' in the Cisco Modeling Labs MCP Server context, alongside sibling tools like 'create_lab', 'create_router', 'create_link_v3', and 'configure_node'.
Attacks that exploit this kind of access
create_switch. It is categorised as a Write tool in the Claude-Modeling-Labs MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude-Modeling-Labs MCP Server MCP server in PolicyLayer and add a rule for create_switch: 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.
create_switch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_switch 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 create_switch. 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.
create_switch 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 →