# execute_js

Run JS in a sandbox, capture output (300 sats/call; free tier 100 calls/mo)

Agent View of the PolicyLayer registry record for `execute_js`. HTML page: https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/execute-js

## Facts

- Tool: `execute_js`
- Server: Hyperion (`https://hyperion.thetempleofdoom.com/mcp`) — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion.md
- Homepage: https://github.com/https://hyperion.thetempleofdoom.com/mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `code` | string | yes | JavaScript expression or script snippet. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "execute_js",
    "arguments": {
      "code": "<code>"
    }
  }
}
```

## Why execute_js is rated High

execute_js triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Risk signals: Accepts freeform code/query input (code)

## Use case

AI agents invoke execute_js to trigger actions in Hyperion. 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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Hyperion:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_js": {
      "limits": [
        {
          "counter": "execute_js_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Hyperion (354)

- `cron` — Execute — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/cron.md
- `o_csp_parse` — Execute — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/o-csp-parse.md
- `o_transform` — Execute — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/o-transform.md
- `ascii` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/ascii.md
- `chart` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/chart.md
- `data_convert` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/data-convert.md
- `diff` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/diff.md
- `echo_beacon` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/echo-beacon.md
- `echo_order` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/echo-order.md
- `echo_tts` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/echo-tts.md
- `encode` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/encode.md
- `fc_map` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/fc-map.md
- `fc_scrape` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/fc-scrape.md
- `fc_search` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/fc-search.md
- `hash` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/hash.md
- `http_client` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/http-client.md
- `lynx_inspect` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/lynx-inspect.md
- `lynx_recon` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/lynx-recon.md
- `lynx_steg` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/lynx-steg.md
- `math` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/math.md
- `mcp_discover` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/mcp-discover.md
- `mcp_readme` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/mcp-readme.md
- `mcp_stats` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/mcp-stats.md
- `mobsf_report` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/mobsf-report.md
- `mobsf_scans` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/mobsf-scans.md
- `netutils` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/netutils.md
- `o_abusecontact` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/o-abusecontact.md
- `o_agify` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/o-agify.md
- `o_airquality` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/o-airquality.md
- `o_antipode` — Read — https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion/o-antipode.md
- …and 324 more: https://policylayer.com/tools/com-thetempleofdoom-hyperion-hyperion.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-thetempleofdoom-hyperion-hyperion · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-thetempleofdoom-hyperion-hyperion