# ai_agent

Run a prompt through Apple

Agent View of the PolicyLayer registry record for `ai_agent`. HTML page: https://policylayer.com/tools/io-github-heznpc-iconnect/ai-agent

## Facts

- Tool: `ai_agent`
- Server: Iconnect (`iconnect-mcp`) — https://policylayer.com/tools/io-github-heznpc-iconnect.md
- Install: `npx -y iconnect-mcp`
- Homepage: https://github.com/heznpc/iConnect
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ai_agent",
    "arguments": {}
  }
}
```

## Why ai_agent is rated High

The 'ai_agent' tool executes arbitrary prompts through an Apple AI system. While the description is somewhat terse, the combination of 'Run' (verb indicating execution) and 'prompt' (variable user input) classifies this as Execute rather than Read.

From the tool's own definition: "Tool name 'ai_agent' combined with description 'Run a prompt through Apple' indicates execution of an AI agent with arbitrary prompts. This is an Execute operation that runs code/models whose effects depend on the prompt argument."

## Use case

AI agents invoke ai_agent to trigger actions in Iconnect. 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 Iconnect:

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

## Other tools on Iconnect (278)

- `delete_contact` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-contact.md
- `delete_event` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-event.md
- `delete_note` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-note.md
- `delete_photos` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-photos.md
- `delete_playlist` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-playlist.md
- `delete_reminder` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-reminder.md
- `delete_reminder_list` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-reminder-list.md
- `delete_shortcut` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/delete-shortcut.md
- `memory_forget` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/memory-forget.md
- `move_note` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/move-note.md
- `remove_from_playlist` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/remove-from-playlist.md
- `semantic_clear` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/semantic-clear.md
- `spotlight_clear` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/spotlight-clear.md
- `trash_file` — Destructive — https://policylayer.com/tools/io-github-heznpc-iconnect/trash-file.md
- `activate_tab` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/activate-tab.md
- `ai_chat` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/ai-chat.md
- `ai_plan_metrics` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/ai-plan-metrics.md
- `connect_bluetooth` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/connect-bluetooth.md
- `disconnect_bluetooth` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/disconnect-bluetooth.md
- `edit_shortcut` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/edit-shortcut.md
- `event_subscribe` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/event-subscribe.md
- `generate_image` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/generate-image.md
- `generate_text` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/generate-text.md
- `gws_raw` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/gws-raw.md
- `import_shortcut` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/import-shortcut.md
- `keynote_start_slideshow` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/keynote-start-slideshow.md
- `launch_app` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/launch-app.md
- `local_llm_generate` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/local-llm-generate.md
- `minimize_window` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/minimize-window.md
- `move_window` — Execute — https://policylayer.com/tools/io-github-heznpc-iconnect/move-window.md
- …and 248 more: https://policylayer.com/tools/io-github-heznpc-iconnect.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=io-github-heznpc-iconnect · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-heznpc-iconnect