Connect to VNA at specified host:port
AI agents use vna_connect to create or update resources in Copper Mountain Vna — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Copper Mountain Vna environment.
Establishing a TCP/IP connection to a physical instrument (VNA) creates a new network session/resource binding. It is not purely read-only (it opens a persistent connection and sets up state on both sides), not destructive, and not financial. 'Write' best captures the side-effectful nature of initiating an external connection that enables subsequent control of lab hardware.
From the tool's definition Connect to VNA at specified host:port
Attacks that exploit this kind of access
Connect to VNA at specified host:port. It is categorised as a Write tool in the Copper Mountain Vna MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Copper Mountain Vna MCP server in PolicyLayer and add a rule for vna_connect: 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 Copper Mountain Vna. Nothing to install.
vna_connect 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 vna_connect 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 vna_connect. 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.
vna_connect is provided by the Copper Mountain Vna MCP server (rfingadam/copper-mountain-vna-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 →