save_learned_command · Instrument MCP Server MCP

WHAT IT DOES

What save_learned_command does on Instrument MCP Server

AI agents use save_learned_command to create or update resources in Instrument MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Instrument MCP Server environment.

WHY IT NEEDS A POLICY

Why save_learned_command needs a policy

This tool writes/creates new command definitions to storage (likely a local database or config file). While reversible via deletion or editing, it could allow an AI agent to persistently inject malicious SCPI sequences into learned commands that execute on instruments during later sessions, affecting test integrity or instrument behavior.

From the tool's definition Tool name 'save_learned_command' indicates persistent storage of command definitions. Server context involves SCPI (Standard Commands for Programmable Instruments) which can control test equipment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_learned_command Rate-limited

save_learned_command stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_learned_command": {
      "limits": [
        {
          "counter": "save_learned_command_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Instrument MCP Server, so you can run agents against it safely.

FAQ

Questions about save_learned_command

What does the save_learned_command tool do? +

save_learned_command. It is categorised as a Write tool in the Instrument MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_learned_command? +

Register the Instrument MCP Server MCP server in PolicyLayer and add a rule for save_learned_command: 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 Instrument MCP Server. Nothing to install.

What risk level is save_learned_command? +

save_learned_command is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_learned_command? +

Yes. Add a rate_limit block to the save_learned_command 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.

How do I block save_learned_command completely? +

Set action: deny in the PolicyLayer policy for save_learned_command. 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.

What MCP server provides save_learned_command? +

save_learned_command is provided by the Instrument MCP Server MCP server (zeng-andrew/instrument-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.