// SCAN REPORT

Mcp Ssh Tool

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

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

Last updated: 2 Jul 2026

13 can modify or destroy data

7 read-only

20 tools total

Community server · catalogue entry verified 02/07/2026

How to control Mcp Ssh Tool ↓

TOOL MAP

What Mcp Ssh Tool exposes to your agents

Read (7) Write / Execute (12) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Ssh Tool tools

Destructive · Critical fs_rmrf Recursive file/directory removal is inherently irreversible. Execute · High ensure_package Installing or removing packages modifies system state by invoking package managers (apt, yum, etc.) on a remote host. Execute · High ensure_service Controlling system services (start/stop/restart/enable/disable) is an Execute-level action with high blast radius: an AI agent could stop critical services, cause outages, or enable unauthorized services on remote machin Execute · Critical proc_exec This tool runs arbitrary commands on a remote system via SSH.

13 of Mcp Ssh Tool'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 Ssh Tool

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

Deny destructive operations

{
  "fs_rmrf": {
    "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

{
  "ensure_lines_in_file": {
    "limits": [
      {
        "counter": "ensure_lines_in_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "fs_list": {
    "limits": [
      {
        "counter": "fs_list_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 Ssh Tool — 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 SSH TOOL →

Instant setup, no code required.

FULL CATALOGUE

All 20 Mcp Ssh Tool tools

DESTRUCTIVE 1 tools

Destructive fs_rmrf Removes files or directories recursively

EXECUTE 5 tools

Execute ensure_package Ensures a package is installed or removed Execute ensure_service Ensures a service is in the desired state Execute proc_exec Executes a command on the remote system Execute proc_sudo Executes a command with sudo privileges Execute ssh_open_session Opens a new SSH session with authentication

WRITE 7 tools

Write ensure_lines_in_file Ensures specific lines are present or absent in a file Write fs_mkdirp Creates directories recursively Write fs_rename Renames or moves a file/directory Write fs_write Writes data to a file on the remote system Write patch_apply Applies a patch to a file Write ssh_close_session Closes an SSH session Write ssh_ping Checks if an SSH session is still alive and responsive

READ 7 tools

Read fs_list Lists directory contents Read fs_read Reads a file from the remote system Read fs_stat Gets file or directory statistics Read os_detect Detects operating system and environment information Read ssh_list_configured_hosts Lists all hosts configured in ~/.ssh/config Read ssh_list_sessions Lists all active SSH sessions with their details Read ssh_resolve_host Resolves a host alias from ~/.ssh/config to connection parameters

FAQ

Questions about Mcp Ssh Tool

Can an AI agent delete data through the Mcp Ssh Tool MCP server? +

Yes. The Mcp Ssh Tool server exposes 1 destructive tools including fs_rmrf. 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 Mcp Ssh Tool? +

The Mcp Ssh Tool server has 7 write tools including ensure_lines_in_file, fs_mkdirp, fs_rename. 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 Ssh Tool.

How many tools does the Mcp Ssh Tool MCP server expose? +

20 tools across 2 categories: Read, Write. 7 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Mcp Ssh Tool? +

Register the Mcp Ssh Tool 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 Ssh Tool tool call.

Deterministic rules across all 20 Mcp Ssh Tool tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP SSH TOOL →

Instant setup, no code required.

20 Mcp Ssh Tool tools catalogued and risk-classified — across an index of 43,000+ MCP servers.