# run_shell

A execute tool on the Allcanuse MCP server.

Agent View of the PolicyLayer registry record for `run_shell`. HTML page: https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/run-shell

## Facts

- Tool: `run_shell`
- Server: Allcanuse (`ra1nyxin/allcanuse-mcp`) — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp.md
- Homepage: https://github.com/ra1nyxin/allcanuse-mcp
- 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": "run_shell",
    "arguments": {}
  }
}
```

## Why run_shell is rated High

Shell execution is the highest-risk operation available to an AI agent outside of financial transactions. Any shell command can be run, including data destruction, system compromise, credential theft, lateral movement, or denial of service. Blast radius is unlimited and depends entirely on system permissions and agent behavior.

From the tool's own definition: "Tool name 'run_shell' directly indicates shell command execution capability. Server description confirms 'command execution' among its capabilities. No description provided for the tool itself, but the name unambiguously denotes arbitrary code execution."

## Use case

AI agents invoke run_shell to trigger actions in Allcanuse. 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 Allcanuse:

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

## Other tools on Allcanuse (129)

- `cancel_background_task` — Destructive — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/cancel-background-task.md
- `delete_path` — Destructive — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/delete-path.md
- `kill_process` — Destructive — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/kill-process.md
- `capture_camera_photo` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/capture-camera-photo.md
- `capture_screenshot` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/capture-screenshot.md
- `check_c_syntax` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/check-c-syntax.md
- `compile_c_program` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/compile-c-program.md
- `create_background_task` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/create-background-task.md
- `deploy_and_update_service` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/deploy-and-update-service.md
- `evaluate_c_math_expression` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/evaluate-c-math-expression.md
- `extract_archive` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/extract-archive.md
- `format_c_code` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/format-c-code.md
- `generate_c_build_files` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/generate-c-build-files.md
- `generate_c_numeric_test_harness` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/generate-c-numeric-test-harness.md
- `http_request` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/http-request.md
- `optimize_images_for_memory` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/optimize-images-for-memory.md
- `pause_background_task` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/pause-background-task.md
- `ping_host` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/ping-host.md
- `preprocess_c_source` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/preprocess-c-source.md
- `raw_tcp_exchange` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/raw-tcp-exchange.md
- `resume_background_task` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/resume-background-task.md
- `run_cmd` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/run-cmd.md
- `run_powershell` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/run-powershell.md
- `scan_ports` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/scan-ports.md
- `start_managed_process` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/start-managed-process.md
- `start_process` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/start-process.md
- `stop_managed_process` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/stop-managed-process.md
- `tcp_connect` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/tcp-connect.md
- `trace_route` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/trace-route.md
- `udp_send_receive` — Execute — https://policylayer.com/tools/ra1nyxin-allcanuse-mcp/udp-send-receive.md
- …and 99 more: https://policylayer.com/tools/ra1nyxin-allcanuse-mcp.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=ra1nyxin-allcanuse-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ra1nyxin-allcanuse-mcp