// SCAN REPORT

Desktop Commander

11 tools. 4 can modify or destroy data without limits.

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

Last updated: 12 Aug 2026

4 can modify or destroy data

7 read-only

11 tools total

Community server · catalogue entry checked 12/08/2026

How to control Desktop Commander ↓

TOOL MAP

What Desktop Commander exposes to your agents

Read (7) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Desktop Commander tools

Destructive · High force_terminate Force terminating a terminal session is irreversible — any unsaved state, running processes, or in-progress operations are permanently lost. Write · Medium create_directory Creating directories is a reversible modification to the filesystem. Write · High move_file Moving and renaming files are write operations that modify file system metadata and organization reversibly. Write · High set_config_value This tool modifies system configuration settings that control security boundaries (blocked commands, allowed directories, file operation limits).

4 of Desktop Commander's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Desktop Commander

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

Deny destructive operations

{
  "force_terminate": {
    "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

{
  "create_directory": {
    "limits": [
      {
        "counter": "create_directory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_config": {
    "limits": [
      {
        "counter": "get_config_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 Desktop Commander — 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 DESKTOP COMMANDER →

Instant setup, no code required.

FULL CATALOGUE

All 11 Desktop Commander tools

DESTRUCTIVE 1 tools

Destructive force_terminate Force terminate a running terminal session. ${CMD_PREFIX_DESC

WRITE 3 tools

Write create_directory Create a new directory or ensure a directory exists. Can crea Write move_file Move or rename files and directories. Can move files between Write set_config_value Set a specific configuration value by key. WARNING: Should be

READ 7 tools

Read get_config Get the complete server configuration as JSON. Config includes fields for: - blockedCo Read get_file_info Retrieve detailed metadata about a file or directory including: - size Read get_recent_tool_calls Get recent tool call history with their arguments and outputs. Returns chronological l Read get_usage_stats Get usage statistics for debugging and analysis. Returns summ Read kill_process Terminate a running process by PID. Use with caution as this will forcefully terminat Read list_processes List all running processes. Returns process information inclu Read list_searches List all active searches. Shows search IDs, search types, pat

EXPLORE

Related servers

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

FAQ

Questions about Desktop Commander

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

Yes. The Desktop Commander server exposes 1 destructive tools including force_terminate. 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 Desktop Commander? +

The Desktop Commander server has 3 write tools including create_directory, move_file, set_config_value. 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 Desktop Commander.

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

11 tools across 3 categories: Destructive, Read, Write. 7 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Desktop Commander? +

Register the Desktop Commander 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 Desktop Commander tool call.

Deterministic rules across all 11 Desktop Commander tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DESKTOP COMMANDER →

Instant setup, no code required.

11 Desktop Commander tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Desktop Commander's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →