run_script

Run a script, optionally with variables.

SERVERHa Nexus Agent SOURCEfistacho/ha-nexus-agent

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/fistacho-ha-nexus-agent/run-script.md

WHAT IT DOES

What run_script does on Ha Nexus Agent

AI agents invoke run_script to trigger actions in Ha Nexus Agent. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why run_script is rated High

This tool executes scripts with user-supplied variables in a smart home automation context. The blast radius is high because scripts can control physical devices (lights, locks, thermostats, security systems) and trigger complex automations. While not irreversibly destructive by itself, script execution is the Execute category because its effects depend entirely on the script content and supplied variables.

From the tool's definition Tool name 'run_script' with description 'Run a script, optionally with variables.' indicates execution of arbitrary scripts with configurable parameters.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_script safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Ha Nexus Agent, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_script, this is the rule to start with:

run_script Rate-limited

run_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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Ha Nexus Agent, apply this rule, and every run_script call is checked against it from then on.

FAQ

Questions about run_script

What does the run_script tool do? +

Run a script, optionally with variables. It is categorised as a Execute tool in the Ha Nexus Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_script? +

Register the Ha Nexus Agent MCP server in PolicyLayer and add a rule for run_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 Ha Nexus Agent. Nothing to install.

What risk level is run_script? +

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

Can I rate-limit run_script? +

Yes. Add a rate_limit block to the run_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 run_script completely? +

Set action: deny in the PolicyLayer policy for run_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 run_script? +

run_script is provided by the Ha Nexus Agent MCP server (fistacho/ha-nexus-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Ha Nexus Agent, and thousands of servers like it.

This server

All 276 Ha Nexus Agent tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP →load_script on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →