run_javascript

Execute JavaScript in a Safari tab. Use list_tabs to find window/tab indices. Returns the result as a string.

SERVERAirMCP SOURCEairmcp

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/heznpc-airmcp/run-javascript.md

WHAT IT DOES

What run_javascript does on AirMCP

AI agents invoke run_javascript to trigger actions in AirMCP. 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_javascript is rated High

This tool executes arbitrary JavaScript in a Safari tab with full access to the DOM, local storage, and potentially sensitive data within the browser context. An AI agent could use this to steal credentials, modify webpage content, exfiltrate data from web applications, perform unauthorized actions on behalf of the user, or establish persistence.

From the tool's definition 'Execute JavaScript in a Safari tab' and 'Returns the result as a string' directly indicate arbitrary code execution capability.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_javascript safely

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

run_javascript Rate-limited

run_javascript 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_javascript": {
      "limits": [
        {
          "counter": "run_javascript_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 AirMCP, apply this rule, and every run_javascript call is checked against it from then on.

FAQ

Questions about run_javascript

What does the run_javascript tool do? +

Execute JavaScript in a Safari tab. Use list_tabs to find window/tab indices. Returns the result as a string. It is categorised as a Execute tool in the AirMCP 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_javascript? +

Register the Air MCP server in PolicyLayer and add a rule for run_javascript: 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 AirMCP. Nothing to install.

What risk level is run_javascript? +

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

Can I rate-limit run_javascript? +

Yes. Add a rate_limit block to the run_javascript 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_javascript completely? +

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

run_javascript is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Air, and thousands of servers like it.

This server

All 279 Air tools → High-risk tools on this server →

Across the catalogue

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

Guides

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