km_add_shell_script

THE RISK

High Risk

Why km_add_shell_script needs a policy

This tool executes arbitrary shell scripts, which can run any command on the system. Shell script execution has a critical blast radius — an AI agent could misuse it to run destructive commands, exfiltrate data, install malware, or cause irreversible system changes. Execute is the correct category (not Destructive) because the tool itself runs commands whose effects depend on the arguments provided.

From the tool's definition "Add an action to execute a shell script"

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

POLICY

How to control km_add_shell_script

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_add_shell_script:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "km_add_shell_script": {
      "limits": [
        {
          "counter": "km_add_shell_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

km_add_shell_script stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Keyboard Maestro tools

Destructive km_delete_action Delete a specific action from a macro. Actions are 1-indexed. WARNING: This cannot be undo Destructive km_delete_macro Delete a macro by name or UID. WARNING: This cannot be undone! Destructive km_delete_trigger Delete a trigger from a macro. Triggers are 1-indexed. Destructive km_manage_group Manage macro groups (create, delete, toggle, list). Execute km_run_macro Execute a macro by name or UID. Execute km_add_execute_macro Add an action to execute another macro. Write km_search_replace_action Search and replace text within a specific action in a macro. Useful for fixing typos or up Write km_add_action Add an action to an existing macro using XML.

All 34 Keyboard Maestro tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Keyboard Maestro → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about km_add_shell_script

What does the km_add_shell_script tool do? +

Add an action to execute a shell script. It is categorised as a Execute tool in the Keyboard Maestro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on km_add_shell_script? +

Register the Keyboard Maestro MCP server in PolicyLayer and add a rule for km_add_shell_script: 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_add_shell_script? +

km_add_shell_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit km_add_shell_script? +

Yes. Add a rate_limit block to the km_add_shell_script 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_add_shell_script completely? +

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

km_add_shell_script 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.

CHECK YOUR STACK →