Medium Risk

km_manage_variable

Manage Keyboard Maestro variables (get, set, delete).

How to control km_manage_variable ↓

What km_manage_variable does on Keyboard Maestro

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

Medium Risk

Why km_manage_variable needs a policy

This tool performs Write operations (set, delete variables) which are reversible data modifications. It's classified as Write rather than Destructive because variable deletion in macro automation is not typically permanent/irreversible in the same sense as deleting files—variables can be recreated.

From the tool's definition Tool description explicitly states it can 'get, set, delete' variables. The 'set' and 'delete' operations modify or remove data; 'get' is read-only but the tool's primary function is management (modification).

Documented attack patterns abuse exactly the kind of access km_manage_variable gives an agent:

How to control km_manage_variable

PolicyLayer is an MCP gateway — it sits between your AI agents and Keyboard Maestro, and nothing reaches the server without passing your rules. This is the rule we recommend for km_manage_variable:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "km_manage_variable": {
      "limits": [
        {
          "counter": "km_manage_variable_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

km_manage_variable 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.

  1. Create a free account and register Keyboard Maestro — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about km_manage_variable

What does the km_manage_variable tool do? +

Manage Keyboard Maestro variables (get, set, delete). It is categorised as a Write tool in the Keyboard Maestro MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on km_manage_variable? +

Register the Keyboard Maestro MCP server in PolicyLayer and add a rule for km_manage_variable: 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 Keyboard Maestro. Nothing to install.

What risk level is km_manage_variable? +

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

Can I rate-limit km_manage_variable? +

Yes. Add a rate_limit block to the km_manage_variable 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 km_manage_variable completely? +

Set action: deny in the PolicyLayer policy for km_manage_variable. 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 km_manage_variable? +

km_manage_variable is provided by the Keyboard Maestro MCP server (saihgupr/keyboard-maestro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Keyboard Maestro tool call.

Start from Keyboard Maestro, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

34 Keyboard Maestro tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.