remote_macos_send_keys

THE RISK

High Risk

Why remote_macos_send_keys needs a policy

Sending arbitrary keyboard input to a macOS system can trigger any action a human could perform via keyboard — launching commands, typing text, invoking shortcuts (e.g., Cmd+Q to quit, Cmd+Delete to delete files), or interacting with any application. This constitutes remote execution of arbitrary operations on the host system.

From the tool's definition Send keyboard input to the local macOS system

Documented attack patterns abuse exactly the kind of access remote_macos_send_keys gives an agent:

POLICY

How to control remote_macos_send_keys

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Remote macOS Control Server, and nothing reaches the server without passing your rules. This is the rule we recommend for remote_macos_send_keys:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "remote_macos_send_keys": {
      "limits": [
        {
          "counter": "remote_macos_send_keys_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

remote_macos_send_keys stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register MCP Remote macOS Control Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Remote macOS Control Server tools

Execute remote_macos_mouse_click Click at specified coordinates on the local macOS screen Execute remote_macos_mouse_double_click Double-click at specified coordinates on the remote macOS screen Execute remote_macos_mouse_drag_n_drop Drag from one location to another (drag and drop operation) Execute remote_macos_mouse_move Move the mouse cursor to specified coordinates Execute remote_macos_mouse_scroll Scroll at specified coordinates in a given direction Execute remote_macos_open_application Open an application on the local macOS system Read remote_macos_get_screen Take a screenshot of the local macOS desktop

All 8 MCP Remote macOS Control Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Remote macOS Control Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about remote_macos_send_keys

What does the remote_macos_send_keys tool do? +

Send keyboard input to the local macOS system. It is categorised as a Execute tool in the MCP Remote macOS Control Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on remote_macos_send_keys? +

Register the MCP Remote macOS Control Server MCP server in PolicyLayer and add a rule for remote_macos_send_keys: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Remote macOS Control Server. Nothing to install.

What risk level is remote_macos_send_keys? +

remote_macos_send_keys is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit remote_macos_send_keys? +

Yes. Add a rate_limit block to the remote_macos_send_keys rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block remote_macos_send_keys completely? +

Set action: deny in the PolicyLayer policy for remote_macos_send_keys. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides remote_macos_send_keys? +

remote_macos_send_keys is provided by the MCP Remote macOS Control Server MCP server (senseisven/mcp_macos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Remote macOS Control Server tool call.

Start from MCP Remote macOS Control Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →