# run_tar

A execute tool on the Pentester-MCP MCP server.

Agent View of the PolicyLayer registry record for `run_tar`. HTML page: https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-tar

## Facts

- Tool: `run_tar`
- Server: Pentester-MCP (`halilkirazkaya/pentester-mcp`) — https://policylayer.com/tools/halilkirazkaya-pentester-mcp.md
- Homepage: https://github.com/halilkirazkaya/pentester-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_tar",
    "arguments": {}
  }
}
```

## Why run_tar is rated High

While 'tar' is primarily an archive tool, it can be weaponized to execute arbitrary code depending on how it is invoked and what arguments an agent provides. On a pentesting server with 200+ tools, 'run_tar' most likely allows execution of tar with user-controlled arguments, making it Execute rather than merely Read.

From the tool's own definition: "Tool name is 'run_tar'; context indicates this is a penetration testing server executing open-source security tools via MCP with Docker sandboxing."

## Use case

AI agents invoke run_tar to trigger actions in Pentester-MCP. 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 Pentester-MCP:

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

## Other tools on Pentester-MCP (336)

- `dnscat_client` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/dnscat-client.md
- `execute_weevely_module` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/execute-weevely-module.md
- `generate_weevely_agent` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/generate-weevely-agent.md
- `identify_hash` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/identify-hash.md
- `john_prepare` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/john-prepare.md
- `launch_xsser_gui` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/launch-xsser-gui.md
- `manage_brew` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/manage-brew.md
- `manage_dirb_dictionaries` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/manage-dirb-dictionaries.md
- `manage_mounts` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/manage-mounts.md
- `manage_sliver_daemon` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/manage-sliver-daemon.md
- `manage_wpprobe` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/manage-wpprobe.md
- `monitor_fping` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/monitor-fping.md
- `objection_explore` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/objection-explore.md
- `objection_patch` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/objection-patch.md
- `run_403bypasser` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-403bypasser.md
- `run_addcomputer` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-addcomputer.md
- `run_aircrack_action` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-aircrack-action.md
- `run_aix` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-aix.md
- `run_alterx` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-alterx.md
- `run_amass` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-amass.md
- `run_apktool` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-apktool.md
- `run_arachni` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-arachni.md
- `run_arjun` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-arjun.md
- `run_asnmap` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-asnmap.md
- `run_atexec` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-atexec.md
- `run_autobloody` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-autobloody.md
- `run_autorecon` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-autorecon.md
- `run_awk` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-awk.md
- `run_bbot` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-bbot.md
- `run_binwalk` — Execute — https://policylayer.com/tools/halilkirazkaya-pentester-mcp/run-binwalk.md
- …and 306 more: https://policylayer.com/tools/halilkirazkaya-pentester-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=halilkirazkaya-pentester-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/halilkirazkaya-pentester-mcp