# ssh-run

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.

Agent View of the PolicyLayer registry record for `ssh-run`. HTML page: https://policylayer.com/tools/io-github-dave-london-cargo/ssh-run

## Facts

- Tool: `ssh-run`
- Server: Cargo (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-cargo.md
- Homepage: https://github.com/Dave-London/pare
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ssh-run",
    "arguments": {}
  }
}
```

## 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 own 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."

## Use case

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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Cargo:

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

## Other tools on Cargo (201)

- `branch` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/branch.md
- `clean` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/clean.md
- `pr-close` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/pr-close.md
- `remove` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/remove.md
- `reset` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/reset.md
- `secret-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/secret-delete.md
- `tag` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/tag.md
- `variable-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/variable-delete.md
- `workspace` — Destructive — https://policylayer.com/tools/io-github-dave-london-cargo/workspace.md
- `add` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/add.md
- `add-package` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/add-package.md
- `ansible-galaxy` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/ansible-galaxy.md
- `ansible-playbook` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/ansible-playbook.md
- `api` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/api.md
- `apply` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/apply.md
- `bazel` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bazel.md
- `biome-check` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/biome-check.md
- `bisect` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bisect.md
- `black` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/black.md
- `build` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/build.md
- `bundle-exec` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bundle-exec.md
- `bundle-install` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/bundle-install.md
- `check` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/check.md
- `cherry-pick` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/cherry-pick.md
- `clippy` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/clippy.md
- `cmake` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/cmake.md
- `compose-build` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/compose-build.md
- `compose-down` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/compose-down.md
- `compose-up` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/compose-up.md
- `conda` — Execute — https://policylayer.com/tools/io-github-dave-london-cargo/conda.md
- …and 171 more: https://policylayer.com/tools/io-github-dave-london-cargo.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-dave-london-cargo · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dave-london-cargo