// SCAN REPORT

SSH MCP Server

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

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

Last updated: 15 Aug 2026

13 can modify or destroy data

10 read-only

23 tools total

Community server · catalogue entry checked 15/08/2026

How to control SSH MCP Server ↓

TOOL MAP

What SSH MCP Server exposes to your agents

Read (10) Write / Execute (9) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous SSH MCP Server tools

Destructive · High cancel_background_job Cancelling a running background job is an irreversible action — the job's in-progress work is terminated and cannot be resumed. Destructive · High remove_ssh_key Revoking/removing an SSH key is an irreversible action that permanently deletes access credentials. Destructive · High revoke_cert Revoking a certificate is an irreversible action that permanently invalidates an SSH certificate. Destructive · High sftp_delete File deletion is a destructive action that cannot be undone.

13 of SSH MCP Server's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control SSH MCP Server

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

Deny destructive operations

{
  "cancel_background_job": {
    "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

{
  "add_ssh_key": {
    "limits": [
      {
        "counter": "add_ssh_key_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_audit_logs": {
    "limits": [
      {
        "counter": "get_audit_logs_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 SSH MCP 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 SSH →

Instant setup, no code required.

FULL CATALOGUE

All 23 SSH MCP Server tools

DESTRUCTIVE 4 tools

Destructive cancel_background_job Cancel a running background job. Destructive remove_ssh_key Revoke / remove an SSH key by its key_id. Destructive revoke_cert Revoke an issued SSH certificate. Destructive sftp_delete Delete a remote file via SFTP.

EXECUTE 5 tools

Execute approve_request Approve a pending approval request. Execute request_approval Request approval for a privileged (Tier 2) operation. Execute run_ssh_command run_ssh_command Execute run_ssh_command_background run_ssh_command_background Execute ssh_connect Open a persistent SSH session to a host.

WRITE 4 tools

Write add_ssh_key Register a new SSH public key with policy checks. Write issue_cert Issue a short-lived SSH certificate for a user. Write ssh_disconnect Close a persistent SSH session. Write transfer_file transfer_file

READ 10 tools

Read get_audit_logs Return the last N audit log entries. Read-only. Read get_host_facts Get safe host metadata (OS, uptime, kernel) — no secrets. Read list_background_jobs List all background jobs (running + completed). Read list_hosts List all allowed SSH hosts with metadata (labels, roles, description). Read list_pending_approvals List all pending approval requests. Read list_templates List all available command templates that can be used with run_ssh_command. Read poll_background_job Read accumulated output and status of a background job (redacted). Read sftp_list_directory List files and directories at a remote path. Read ssh_list_sessions List all active SSH sessions and remaining connection slots. Read ssh_session_ping Health-check a persistent SSH session.

EXPLORE

Related servers

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

FAQ

Questions about SSH MCP Server

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

Yes. The SSH MCP Server server exposes 4 destructive tools including cancel_background_job, remove_ssh_key, revoke_cert. 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 SSH MCP Server? +

The SSH MCP Server server has 4 write tools including add_ssh_key, issue_cert, 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 SSH MCP Server.

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

23 tools across 5 categories: Destructive, Execute, Financial, Read, Write. 10 are read-only. 13 can modify, create, or delete data.

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

Register the SSH MCP 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 SSH MCP Server tool call.

Deterministic rules across all 23 SSH MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SSH →

Instant setup, no code required.

23 SSH MCP Server tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from SSH MCP Server'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 →