// SCAN REPORT

Claude Desktop Commander MCP

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

2 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

9 can modify or destroy data

10 read-only

19 tools total

Community server · catalogue entry verified 12/06/2026

How to control Claude Desktop Commander MCP ↓

TOOL MAP

What Claude Desktop Commander MCP exposes to your agents

Read (10) Write / Execute (7) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Claude Desktop Commander MCP tools

Destructive · High force_terminate Force terminating a running session is an irreversible action — the session, its state, and any unsaved in-progress work are permanently destroyed. Destructive · High kill_process Killing a process is an irreversible action — the process is terminated immediately and any unsaved state is lost. Execute · High unblock_command This tool modifies the security policy of the MCP server by removing commands from the blacklist, enabling previously blocked (potentially dangerous) commands to be executed. Execute · Critical execute_command This tool enables arbitrary command execution on the host system with full access to the user's computer.

9 of Claude Desktop Commander MCP's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Claude Desktop Commander MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Desktop Commander MCP, 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

{
  "block_command": {
    "limits": [
      {
        "counter": "block_command_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_file_info": {
    "limits": [
      {
        "counter": "get_file_info_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 Claude Desktop Commander MCP — 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 CLAUDE DESKTOP COMMANDER →

Free to start. No card required.

FULL CATALOGUE

All 19 Claude Desktop Commander MCP tools

DESTRUCTIVE 2 tools

Destructive force_terminate Force terminate a running terminal session. Destructive kill_process Terminate a running process by PID. Use with caution as this will

EXECUTE 2 tools

Execute unblock_command Remove a command from the blacklist. Once unblocked, the command can be executed normally. Execute execute_command Execute a terminal command with timeout. Command will continue running in background if it doesn

WRITE 5 tools

Write block_command Add a command to the blacklist. Once blocked, the command cannot be executed until unblocked. Write create_directory Create a new directory or ensure a directory exists. Can create multiple Write edit_block Apply surgical text replacements to files. Best for small changes (<20% of file size). Write move_file Move or rename files and directories. Can move files between directories Write write_file Completely replace file contents. Best for large changes (>20% of file) or when edit_block fails.

READ 10 tools

Read get_file_info Retrieve detailed metadata about a file or directory including size, Read list_allowed_directories Returns the list of directories that this server is allowed to access. Read list_blocked_commands List all currently blocked commands. Read list_directory Get a detailed listing of all files and directories in a specified path. Read list_processes List all running processes. Returns process information including PID, Read list_sessions List all active terminal sessions. Read read_file Read the complete contents of a file from the file system. Read read_multiple_files Read the contents of multiple files simultaneously. Read read_output Read new output from a running terminal session. Read search_files Recursively search for files and directories matching a pattern.

EXPLORE

Related servers

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

FAQ

Questions about Claude Desktop Commander MCP

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

Yes. The Claude Desktop Commander MCP server exposes 2 destructive tools including force_terminate, kill_process. 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 Claude Desktop Commander MCP? +

The Claude Desktop Commander MCP server has 5 write tools including block_command, create_directory, edit_block. 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 Claude Desktop Commander MCP.

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

19 tools across 4 categories: Destructive, Execute, Read, Write. 10 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on Claude Desktop Commander MCP? +

Register the Claude 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 Claude Desktop Commander MCP tool call.

Deterministic rules across all 19 Claude Desktop Commander MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE DESKTOP COMMANDER →

Free to start. No card required.

19 Claude Desktop Commander MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.