# 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-docker/ssh-run

## Facts

- Tool: `ssh-run`
- Server: Docker (`@paretools/docker`) — https://policylayer.com/tools/io-github-dave-london-docker.md
- Install: `npx -y @paretools/docker`
- 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 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 own 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."

## Use case

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.

## Recommended policy (PolicyLayer)

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

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

## Other tools on Docker (201)

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