// SCAN REPORT

Macinput

12 tools. 9 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

9 can modify or destroy data

3 read-only

12 tools total

Community server · catalogue entry verified 03/07/2026

How to control Macinput ↓

TOOL MAP

What Macinput exposes to your agents

Read (3) Write / Execute (8) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Macinput tools

Destructive · Medium cleanup_screenshot_file The tool explicitly removes/deletes a file. Execute · High click_mouse Mouse clicking triggers UI interactions on the desktop — buttons, links, menus, confirmations — whose effects depend entirely on what is under the cursor at execution time. Execute · High keyboard_key_down Holding a key down is an active execution of a desktop GUI action that can trigger keyboard shortcuts, modify system state, or initiate complex UI interactions. Execute · Medium keyboard_key_up Releasing a held key is a desktop GUI execution primitive.

9 of Macinput's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Macinput

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

Deny destructive operations

{
  "cleanup_screenshot_file": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

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

Cap read operations

{
  "capture_screenshot": {
    "limits": [
      {
        "counter": "capture_screenshot_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Macinput — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MACINPUT →

Instant setup, no code required.

FULL CATALOGUE

All 12 Macinput tools

DESTRUCTIVE 1 tools

Destructive cleanup_screenshot_file Remove a screenshot file created by capture_screenshot.

EXECUTE 8 tools

Execute click_mouse Click at the current cursor location or at explicit coordinates. Execute keyboard_key_down Hold a key down. Pair with keyboard_key_up if you need manual control. Execute keyboard_key_up Release a key previously pressed down. Execute move_mouse Move the cursor to absolute screen coordinates. Execute paste_text_input Paste plain text into the focused target via clipboard and Cmd+V. Execute press_keyboard_key Press and release a key with optional modifiers. Execute scroll_mouse Scroll the mouse wheel by line units. Execute type_text_input Type unicode text into the currently focused macOS input target.

READ 3 tools

Read capture_screenshot Capture the full screen and return a temporary PNG path. Read get_mouse_position Return the current mouse position. Read get_server_settings Return the active safety-related server settings.

FAQ

Questions about Macinput

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

Yes. The Macinput server exposes 1 destructive tools including cleanup_screenshot_file. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Macinput MCP server expose? +

12 tools across 2 categories: Read, Write. 3 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on Macinput? +

Register the Macinput 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 Macinput tool call.

Deterministic rules across all 12 Macinput tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MACINPUT →

Instant setup, no code required.

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