# 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-go/ssh-run

## Facts

- Tool: `ssh-run`
- Server: Go (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-go.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 executes arbitrary shell commands on remote machines, which is a classic Execute operation. While potentially destructive depending on the command argument, the primary capability is command execution on external systems. The high severity reflects the broad blast radius—an AI agent misusing this tool could compromise remote infrastructure, exfiltrate data, disrupt services, or pivot to other systems.

From the tool's own definition: "Tool description states 'Executes a command on a remote host via SSH' and explicitly warns 'This runs commands on a remote machine.' The tool runs arbitrary commands on external systems with full access to their execution environment."

## Use case

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

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

## Other tools on Go (201)

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