ssh-run

SERVERCargo SOURCEDave-London/Pare

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-cargo/ssh-run.md

WHAT IT DOES

What ssh-run does on Cargo

AI agents invoke ssh-run to trigger actions in Cargo. 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 allows execution of arbitrary commands on remote hosts, which is a classic Execute category capability. The severity is high because: (1) command execution on remote machines has potentially broad blast radius depending on command arguments and target host permissions, (2) the warning in the description acknowledges the risk, and (3) misuse could lead to unauthorized code execution, lateral movement, or…

From the tool's definition Tool description explicitly states 'Executes a command on a remote host via SSH' and emphasizes 'runs commands on a remote machine.' It returns stdout, stderr, and exit code, indicating arbitrary command execution capability.

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 Cargo, 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 Cargo, 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 Cargo 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 Cargo 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 Cargo. 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 Cargo MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Cargo, and thousands of servers like it.

This server

All 202 Cargo 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 →