keyboard_press

THE RISK

High Risk

Why keyboard_press needs a policy

This tool sends keyboard input to a browser, including modifier keys and shortcuts. This constitutes executing browser actions with potentially wide-ranging effects — shortcuts could trigger saves, deletions, navigation, form submissions, or system-level actions within the browser context.

From the tool's definition Send keyboard events with support for modifier keys and repetition. Ideal for arrow keys, shortcuts, and special key combinations.

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

POLICY

How to control keyboard_press

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

policy.json

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

keyboard_press 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 Firefox MCP 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 Firefox MCP Server tools

Destructive debug_buffers_clear Clear accumulated debug data buffers to free memory and start fresh monitoring. Destructive browser_close Close the entire browser instance and clean up all sessions and resources. Destructive session_close Close a specific browser session and clean up its resources. Execute browser_launch Launch Firefox browser with multi-session support and comprehensive debugging capabilities Execute debug_monitoring_start Start or restart comprehensive monitoring for console logs, errors, network activity, and Execute element_wait Wait for specific elements to appear or become visible. Essential for handling dynamic con Execute javascript_execute Execute custom JavaScript code in the browser context. Powerful for advanced DOM manipulat Execute page_navigate Navigate to a specific URL in the browser. Works with any web page or web application.

All 29 Firefox MCP 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 Firefox MCP 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 keyboard_press

What does the keyboard_press tool do? +

Send keyboard events with support for modifier keys and repetition. Ideal for arrow keys, shortcuts, and special key combinations. It is categorised as a Execute tool in the Firefox MCP 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 keyboard_press? +

Register the Firefox MCP Server MCP server in PolicyLayer and add a rule for keyboard_press: 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 Firefox MCP Server. Nothing to install.

What risk level is keyboard_press? +

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

Can I rate-limit keyboard_press? +

Yes. Add a rate_limit block to the keyboard_press 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 keyboard_press completely? +

Set action: deny in the PolicyLayer policy for keyboard_press. 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 keyboard_press? +

keyboard_press is provided by the Firefox MCP Server MCP server (jediluke/firefox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Firefox MCP Server tool call.

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

CHECK YOUR STACK →