# 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-npm/ssh-run

## Facts

- Tool: `ssh-run`
- Server: Npm (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-npm.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 arbitrary command execution on remote systems via SSH. While the warning indicates the developer expects careful usage, the capability to execute any command on a remote host represents a significant risk of unintended side effects if an AI agent misuses it (e.g., executing destructive commands, installing malware, exfiltrating data, or disrupting services).

From the tool's own definition: "Tool description explicitly states 'Executes a command on a remote host via SSH' and 'runs commands on a remote machine.' The warning message confirms it has unrestricted command execution capabilities."

## Use case

AI agents invoke ssh-run to trigger actions in Npm. 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 Npm:

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

## Other tools on Npm (201)

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