# run_jsx_json

Run JSX inside the shared JSON wrapper and return the parsed JSON payload.

Agent View of the PolicyLayer registry record for `run_jsx_json`. HTML page: https://policylayer.com/tools/synthetic-ai-ae-mcp/run-jsx-json

## Facts

- Tool: `run_jsx_json`
- Server: Ae (`@synthetic-ai/ae-mcp`) — https://policylayer.com/tools/synthetic-ai-ae-mcp.md
- Install: `npx -y @synthetic-ai/ae-mcp`
- Homepage: https://www.npmjs.com/package/@synthetic-ai/ae-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `timeoutMs` | number | no | Process timeout in milliseconds. Defaults to 120000. |
| `scriptBody` | string | yes | JSX body. Call __write(payload) to return structured data. |

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": "run_jsx_json",
    "arguments": {
      "scriptBody": "<scriptBody>"
    }
  }
}
```

## Why run_jsx_json is rated High

run_jsx_json 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.

## Use case

AI agents invoke run_jsx_json to trigger actions in Ae. 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 Ae:

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

## Other tools on Ae (225)

- `cancel_render` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/cancel-render.md
- `clear_guides` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/clear-guides.md
- `clear_proxy` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/clear-proxy.md
- `clear_render_queue` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/clear-render-queue.md
- `consolidate_footage` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/consolidate-footage.md
- `delete_comp` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/delete-comp.md
- `delete_items` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/delete-items.md
- `delete_layers` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/delete-layers.md
- `delete_mask` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/delete-mask.md
- `parent_layer` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/parent-layer.md
- `purge_caches` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/purge-caches.md
- `reduce_project` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/reduce-project.md
- `remove_comp_marker` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-comp-marker.md
- `remove_effect` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-effect.md
- `remove_guide` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-guide.md
- `remove_keyframes` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-keyframes.md
- `remove_layer_marker` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-layer-marker.md
- `remove_property_from_mogrt` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-property-from-mogrt.md
- `remove_render_queue_item` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-render-queue-item.md
- `remove_shape_group` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-shape-group.md
- `remove_text_animator` — Destructive — https://policylayer.com/tools/synthetic-ai-ae-mcp/remove-text-animator.md
- `new_project` — Execute — https://policylayer.com/tools/synthetic-ai-ae-mcp/new-project.md
- `run_jsx` — Execute — https://policylayer.com/tools/synthetic-ai-ae-mcp/run-jsx.md
- `ae_dialogs` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/ae-dialogs.md
- `find_project_items` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/find-project-items.md
- `get_ae_version` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/get-ae-version.md
- `get_all_property_values` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/get-all-property-values.md
- `get_comp_info` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/get-comp-info.md
- `get_expression` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/get-expression.md
- `get_expression_globals` — Read — https://policylayer.com/tools/synthetic-ai-ae-mcp/get-expression-globals.md
- …and 195 more: https://policylayer.com/tools/synthetic-ai-ae-mcp.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=synthetic-ai-ae-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/synthetic-ai-ae-mcp