# cli_run

A execute tool on the Mcp Anything MCP server.

Agent View of the PolicyLayer registry record for `cli_run`. HTML page: https://policylayer.com/tools/mcp-anything/cli-run

## Facts

- Tool: `cli_run`
- Server: Mcp Anything (`Zaymadkid/mcp-anything`) — https://policylayer.com/tools/mcp-anything.md
- Homepage: https://github.com/Zaymadkid/mcp-anything
- 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": "cli_run",
    "arguments": {}
  }
}
```

## Why cli_run is rated High

Despite the empty description, the name 'cli_run' unambiguously indicates command execution capability. CLI runners execute arbitrary shell commands with effects that depend entirely on the arguments provided. This poses significant risk if misused by an AI agent (could modify files, spawn processes, access systems).

From the tool's own definition: "Tool name 'cli_run' combined with server description mentioning '50+ CLI-Anything harnesses' indicates execution of command-line operations. The tool name explicitly suggests running CLI commands."

## Use case

AI agents invoke cli_run to trigger actions in Mcp Anything. 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 Mcp Anything:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "cli_run": {
      "limits": [
        {
          "counter": "cli_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Mcp Anything (260)

- `cli_uninstall` — Destructive — https://policylayer.com/tools/mcp-anything/cli-uninstall.md
- `component_remove` — Destructive — https://policylayer.com/tools/mcp-anything/component-remove.md
- `cookie_clear` — Destructive — https://policylayer.com/tools/mcp-anything/cookie-clear.md
- `cookie_delete` — Destructive — https://policylayer.com/tools/mcp-anything/cookie-delete.md
- `doc_paragraph_remove` — Destructive — https://policylayer.com/tools/mcp-anything/doc-paragraph-remove.md
- `doc_remove_element` — Destructive — https://policylayer.com/tools/mcp-anything/doc-remove-element.md
- `filter_remove` — Destructive — https://policylayer.com/tools/mcp-anything/filter-remove.md
- `layer_remove` — Destructive — https://policylayer.com/tools/mcp-anything/layer-remove.md
- `network_clear_log` — Destructive — https://policylayer.com/tools/mcp-anything/network-clear-log.md
- `network_remove_interceptor` — Destructive — https://policylayer.com/tools/mcp-anything/network-remove-interceptor.md
- `node_remove` — Destructive — https://policylayer.com/tools/mcp-anything/node-remove.md
- `object_remove` — Destructive — https://policylayer.com/tools/mcp-anything/object-remove.md
- `pres_slide_remove` — Destructive — https://policylayer.com/tools/mcp-anything/pres-slide-remove.md
- `scene_remove` — Destructive — https://policylayer.com/tools/mcp-anything/scene-remove.md
- `script_remove` — Destructive — https://policylayer.com/tools/mcp-anything/script-remove.md
- `selection_none` — Destructive — https://policylayer.com/tools/mcp-anything/selection-none.md
- `session_reset` — Destructive — https://policylayer.com/tools/mcp-anything/session-reset.md
- `sheet_delete` — Destructive — https://policylayer.com/tools/mcp-anything/sheet-delete.md
- `source_remove` — Destructive — https://policylayer.com/tools/mcp-anything/source-remove.md
- `storage_clear_local` — Destructive — https://policylayer.com/tools/mcp-anything/storage-clear-local.md
- `storage_remove_local` — Destructive — https://policylayer.com/tools/mcp-anything/storage-remove-local.md
- `build_configure` — Execute — https://policylayer.com/tools/mcp-anything/build-configure.md
- `build_run` — Execute — https://policylayer.com/tools/mcp-anything/build-run.md
- `cli_by_category` — Execute — https://policylayer.com/tools/mcp-anything/cli-by-category.md
- `cli_install` — Execute — https://policylayer.com/tools/mcp-anything/cli-install.md
- `element_click` — Execute — https://policylayer.com/tools/mcp-anything/element-click.md
- `element_hover` — Execute — https://policylayer.com/tools/mcp-anything/element-hover.md
- `element_scroll_to` — Execute — https://policylayer.com/tools/mcp-anything/element-scroll-to.md
- `form_submit` — Execute — https://policylayer.com/tools/mcp-anything/form-submit.md
- `network_add_interceptor` — Execute — https://policylayer.com/tools/mcp-anything/network-add-interceptor.md
- …and 230 more: https://policylayer.com/tools/mcp-anything.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=mcp-anything · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/mcp-anything