// SCAN REPORT

MCP Desktop Tools

20 tools. 13 can modify or destroy data without limits.

13 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

13 can modify or destroy data

7 read-only

20 tools total

Community server · catalogue entry verified 03/07/2026

How to control MCP Desktop Tools ↓

TOOL MAP

What MCP Desktop Tools exposes to your agents

Read (7) Write / Execute (13) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP Desktop Tools tools

Execute · High browser_navigate Navigation to a URL is an Execute action because it triggers an external operation (browser HTTP request and page load) whose outcome depends on the supplied URL argument. Execute · High desktop_app_launch Launching arbitrary applications is an Execute action because it triggers external operations with effects determined by the arguments (application path/name). Execute · High browser_click Clicking elements in a browser can cause a wide range of side effects: submitting forms, initiating purchases, deleting data, triggering downloads, or navigating to new pages. Execute · High browser_open This tool launches a browser process and navigates to a specified URL, constituting execution of an external operation.

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

POLICY

How to control MCP Desktop Tools

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

Rate limit write operations

{
  "browser_close": {
    "limits": [
      {
        "counter": "browser_close_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "browser_read": {
    "limits": [
      {
        "counter": "browser_read_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 MCP Desktop Tools — 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 MCP DESKTOP TOOLS →

Instant setup, no code required.

FULL CATALOGUE

All 20 MCP Desktop Tools tools

EXECUTE 11 tools

Execute browser_click Click an element on the page by CSS selector Execute browser_navigate Navigate the current browser page to a URL Execute browser_open Launch Chromium browser and navigate to a URL Execute browser_type Type text into an input element on the page Execute desktop_app_launch Launch an application by path, name, or URI Execute desktop_keyboard_hotkey Press a keyboard shortcut (e.g. ctrl+c, alt+tab) Execute desktop_keyboard_type Type text using the keyboard (simulates key presses) Execute desktop_mouse_click Click at screen coordinates using the mouse Execute desktop_mouse_move Move the mouse cursor to screen coordinates Execute desktop_window_focus Focus a window by title (partial match) Execute desktop_window_resize Resize and/or move a window by title

WRITE 2 tools

Write browser_close Close the browser instance Write desktop_clipboard_write Write text to the clipboard

READ 7 tools

Read browser_read Read content from the current page Read browser_screenshot Take a screenshot of the current browser page Read desktop_clipboard_read Read the current clipboard text content Read desktop_window_list List all visible windows with their titles, process names, and positions Read screenshot_fullscreen Capture the entire screen or a specific display Read screenshot_region Capture a rectangular region of the screen Read screenshot_window Capture a specific window by title (partial match)

EXPLORE

Related servers

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

FAQ

Questions about MCP Desktop Tools

How do I prevent bulk modifications through MCP Desktop Tools? +

The MCP Desktop Tools server has 2 write tools including browser_close, desktop_clipboard_write. 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 MCP Desktop Tools.

How many tools does the MCP Desktop Tools MCP server expose? +

20 tools across 3 categories: Execute, Read, Write. 7 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on MCP Desktop Tools? +

Register the MCP Desktop Tools 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 MCP Desktop Tools tool call.

Deterministic rules across all 20 MCP Desktop Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP DESKTOP TOOLS →

Instant setup, no code required.

20 MCP Desktop Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.