ssh_plan_command

THE RISK

High Risk

Why ssh_plan_command needs a policy

This tool creates execution plans for remote commands to be run on SSH servers. Even though it's a planning step rather than direct execution, it prepares arbitrary remote command execution which falls under Execute category. The blast radius is high because these plans can involve any remote command on connected servers, and misuse could stage harmful operations.

From the tool's definition 'Create a reviewed execution plan for a non-trivial remote command' — plans are for executing remote commands on SSH servers

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

POLICY

How to control ssh_plan_command

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

policy.json

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

ssh_plan_command 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 SSH Remote 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 SSH Remote MCP Server tools

Destructive ssh_delete_saved_credentials Delete a saved local SSH credential entry Execute ssh_execute Execute a command on a remote SSH connection Execute ssh_execute_plan Execute an approved command or remote file edit plan Execute ssh_approve_plan Approve a stored plan so it can be executed Execute ssh_connect Connect to a remote Ubuntu server via SSH Execute ssh_connect_saved Connect to a remote server using a saved local SSH credential name Write ssh_plan_edit Create a managed remote file edit plan that requires approval before writing Write ssh_save_credentials Save SSH credentials locally under a reusable name. If a password is provided, the server

All 21 SSH Remote 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 SSH Remote 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_plan_command

What does the ssh_plan_command tool do? +

Create a reviewed execution plan for a non-trivial remote command. It is categorised as a Execute tool in the SSH Remote 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_plan_command? +

Register the SSH Remote MCP Server MCP server in PolicyLayer and add a rule for ssh_plan_command: 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 SSH Remote MCP Server. Nothing to install.

What risk level is ssh_plan_command? +

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

Can I rate-limit ssh_plan_command? +

Yes. Add a rate_limit block to the ssh_plan_command 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_plan_command completely? +

Set action: deny in the PolicyLayer policy for ssh_plan_command. 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_plan_command? +

ssh_plan_command is provided by the SSH Remote MCP Server MCP server (nqmn/adremote-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SSH Remote MCP Server tool call.

Start from SSH Remote 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 →