ssh

THE RISK

High Risk

Why ssh needs a policy

SSH connections allow execution of arbitrary commands on remote systems. An AI agent misusing this tool could run any command on the target host, leading to data exfiltration, system compromise, or destructive actions. The blast radius is critical as it provides interactive shell access to remote infrastructure.

From the tool's definition Connect to a target via SSH

Documented attack patterns abuse exactly the kind of access ssh gives an agent:

POLICY

How to control ssh

PolicyLayer is an MCP gateway — it sits between your AI agents and IT Tools MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for ssh:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ssh": {
      "limits": [
        {
          "counter": "ssh_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

ssh stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register IT Tools MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More IT Tools MCP Server tools

Execute curl Make HTTP requests to web endpoints. Example: GET request to an API or POST data to a serv Execute test_regex Test regular expressions against text Execute decrypt_ansible_vault Decrypt Ansible Vault encrypted text Execute dig Perform DNS lookup with dig command Execute evaluate_math Safely evaluate mathematical expressions Execute generate_otp Generate Time-based One-Time Password (TOTP) codes Execute hash_bcrypt Generate bcrypt hash or verify password against hash Execute ping Test network connectivity to a host. Example: ping google.com to check if it

All 119 IT Tools MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in IT Tools MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ssh

What does the ssh tool do? +

Connect to a target via SSH. It is categorised as a Execute tool in the IT Tools MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ssh? +

Register the IT Tools MCP Server MCP server in PolicyLayer and add a rule for ssh: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches IT Tools MCP Server. Nothing to install.

What risk level is ssh? +

ssh is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ssh? +

Yes. Add a rate_limit block to the ssh rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block ssh completely? +

Set action: deny in the PolicyLayer policy for ssh. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides ssh? +

ssh is provided by the IT Tools MCP Server MCP server (wrenchpilot/it-tools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every IT Tools MCP Server tool call.

Start from IT Tools MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →