# 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-github/ssh-run

## Facts

- Tool: `ssh-run`
- Server: Github (`@paretools/github`) — https://policylayer.com/tools/io-github-dave-london-github.md
- Install: `npx -y @paretools/github`
- 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 executes arbitrary commands on remote hosts, which is a classic Execute category operation. The effects depend entirely on what command is passed as an argument. While not inherently destructive, the blast radius is high because an AI agent could execute harmful commands (data exfiltration, system compromise, credential theft, etc.).

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' with a WARNING about command execution."

## Use case

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

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

## Other tools on Github (201)

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