ssh-run

SERVERDocker SOURCE@paretools/docker

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-docker/ssh-run.md

WHAT IT DOES

What ssh-run does on Docker

AI agents invoke ssh-run to trigger actions in Docker. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why ssh-run is rated High

This tool runs arbitrary commands on external systems via SSH, making it Execute category. Severity is high due to broad blast radius—malicious or erroneous command execution could compromise remote infrastructure, data, or services. The explicit warning reinforces the dangerous nature of this capability. Confidence is very high given unambiguous language describing remote command execution.

From the tool's definition Tool explicitly performs 'Executes a command on a remote host via SSH' and includes warning about running commands on a remote machine. Returns stdout, stderr, exit code indicating arbitrary command execution.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ssh-run safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ssh-run, this is the rule to start with:

ssh-run Rate-limited

ssh-run 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Docker, apply this rule, and every ssh-run call is checked against it from then on.

FAQ

Questions about ssh-run

What does the ssh-run tool do? +

Executes a command on a remote host via SSH. WARNING: This runs commands on a remote machine. Ensure the host and command are correct before executing. Returns structured output with stdout, stderr, exit code, and duration. It is categorised as a Execute tool in the Docker 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-run? +

Register the Docker MCP server in PolicyLayer and add a rule for ssh-run: 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 Docker. Nothing to install.

What risk level is ssh-run? +

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

Can I rate-limit ssh-run? +

Yes. Add a rate_limit block to the ssh-run 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-run completely? +

Set action: deny in the PolicyLayer policy for ssh-run. 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-run? +

ssh-run is provided by the Docker MCP server (@paretools/docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Docker, and thousands of servers like it.

This server

All 202 Docker tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →