PilotGentic

32 tools. 20 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

20 can modify or destroy data
12 read-only
32 tools total

Community server · catalogue entry verified 05/07/2026

How to control PilotGentic ↓

What PilotGentic exposes to your agents

Read (12) Write / Execute (18) Destructive / Financial (2)
Critical Risk

The most dangerous PilotGentic tools

20 of PilotGentic's 32 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control PilotGentic

PolicyLayer is an MCP gateway — it sits between your AI agents and PilotGentic, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "pilotgentic_contacts_manager": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "pilotgentic_calendar_events_manager": {
    "limits": [
      {
        "counter": "pilotgentic_calendar_events_manager_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "pilotgentic_ax_tree": {
    "limits": [
      {
        "counter": "pilotgentic_ax_tree_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register PilotGentic — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON PILOTGENTIC →

Instant setup, no code required.

All 32 PilotGentic tools

READ 12 tools
Read pilotgentic_ax_tree Read the Accessibility (AX) tree of the focused window as structured JSON. Returns roles, labels, values, posi Read pilotgentic_clipboard_history Track, search, and restore clipboard history across sessions. Maintains up to 100 entries in ~/.pilotgentic/cl Read pilotgentic_clipboard_read Read the current macOS clipboard contents. Returns content type (text, rtf, files, image, empty) and decoded t Read pilotgentic_contacts_address_book Full address book access for macOS Contacts.app. op: Read pilotgentic_devtools_network Capture HTTP network requests from a Chrome tab — like the DevTools Network tab. Read pilotgentic_extract_console_logs Extract console logs from Chrome browser tabs using Chrome DevTools Protocol. Can extract from current tab or Read pilotgentic_find Find a UI element by text description, label, or role — returns coordinates and accessibility info for use wit Read pilotgentic_list_skills List all PilotGentic skills: built-in MCP tools and docked third-party extensions. Returns tool names, categor Read pilotgentic_pick Find and describe a UI element at specific coordinates or within a screen region. Read pilotgentic_read_transcript Read recent transcript from Whisper audio transcription output. Returns the last N seconds of transcribed spee Read pilotgentic_search_analytics Analyze tool search usage patterns. Shows most common queries, low-confidence results, and gaps where users se Read pilotgentic_tool_search Search for MacPilot tools by describing what you want to do. Returns the most relevant tools with their names,

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about PilotGentic

Can an AI agent delete data through the PilotGentic MCP server? +

Yes. The PilotGentic server exposes 2 destructive tools including pilotgentic_contacts_manager, pilotgentic_notes_manager. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through PilotGentic? +

The PilotGentic server has 9 write tools including pilotgentic_calendar_events_manager, pilotgentic_clipboard_write, pilotgentic_memory. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach PilotGentic.

How many tools does the PilotGentic MCP server expose? +

32 tools across 4 categories: Destructive, Execute, Read, Write. 12 are read-only. 20 can modify, create, or delete data.

How do I enforce a policy on PilotGentic? +

Register the PilotGentic MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every PilotGentic tool call.

Deterministic rules across all 32 PilotGentic tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

32 PilotGentic tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.