// SCAN REPORT

MCP SSH Server

18 tools. 12 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

12 can modify or destroy data

6 read-only

18 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP SSH Server ↓

TOOL MAP

What MCP SSH Server exposes to your agents

Read (6) Write / Execute (11) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP SSH Server tools

Destructive · Medium ssh_delete_credential Deleting a saved credential is irreversible; once removed, the credential configuration is gone and cannot be recovered without re-entering it. Execute · High ssh_docker_deploy Deploying Docker containers is an Execute operation—it triggers external operations (container instantiation, service startup) whose effects depend on arguments (image, configuration, environment variables). Execute · Critical ssh_execute This tool executes arbitrary commands on remote servers with no stated restrictions on what commands can be run. Execute · Critical ssh_start_interactive_shell This tool grants the ability to execute arbitrary shell commands on remote systems through an interactive terminal session.

12 of MCP SSH Server's 18 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 Server

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

Deny destructive operations

{
  "ssh_delete_credential": {
    "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

{
  "ssh_close_interactive_shell": {
    "limits": [
      {
        "counter": "ssh_close_interactive_shell_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ssh_docker_status": {
    "limits": [
      {
        "counter": "ssh_docker_status_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 Server — 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 →

Instant setup, no code required.

FULL CATALOGUE

All 18 MCP SSH Server tools

DESTRUCTIVE 1 tools

Destructive ssh_delete_credential Delete a saved SSH credential

EXECUTE 6 tools

Execute ssh_connect Connect to an SSH server Execute ssh_connect_with_credential Connect to SSH server using saved credentials Execute ssh_docker_deploy Deploy Docker containers with working directory context Execute ssh_execute Execute a command on a remote SSH server Execute ssh_send_input Send input to an interactive shell session with optional typing simulation Execute ssh_start_interactive_shell Start an interactive shell session with PTY support for typing simulation

WRITE 5 tools

Write ssh_close_interactive_shell Close an interactive shell session Write ssh_copy_file Copy files between local and remote servers or between remote servers Write ssh_disconnect Disconnect from an SSH server Write ssh_save_credential Save SSH credentials for reuse Write ssh_set_working_directory Set the current working directory for a connection

READ 6 tools

Read ssh_docker_status Check Docker container status in working directory Read ssh_file_info Get file information (size, permissions, etc.) Read ssh_get_working_directory Get the current working directory for a connection Read ssh_list_credentials List all saved SSH credentials Read ssh_list_files List files and directories on local or remote server Read ssh_read_output Read output from an interactive shell session

EXPLORE

Related servers

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

FAQ

Questions about MCP SSH Server

Can an AI agent delete data through the MCP SSH Server MCP server? +

Yes. The MCP SSH Server server exposes 1 destructive tools including ssh_delete_credential. 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 Server? +

The MCP SSH Server server has 5 write tools including ssh_close_interactive_shell, ssh_copy_file, ssh_disconnect. 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 Server.

How many tools does the MCP SSH Server MCP server expose? +

18 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on MCP SSH Server? +

Register the MCP SSH Server 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 Server tool call.

Deterministic rules across all 18 MCP SSH Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP SSH →

Instant setup, no code required.

18 MCP SSH Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.