# run_tool

A execute tool on the Nyxstrike MCP server.

Agent View of the PolicyLayer registry record for `run_tool`. HTML page: https://policylayer.com/tools/nyxstrike/run-tool

## Facts

- Tool: `run_tool`
- Server: Nyxstrike (`CommonHuman-Lab/nyxstrike`) — https://policylayer.com/tools/nyxstrike.md
- Homepage: https://github.com/CommonHuman-Lab/nyxstrike
- 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_tool",
    "arguments": {}
  }
}
```

## Why run_tool is rated High

The tool name 'run_tool' is generic but appears designed to execute arbitrary tools on a penetration testing platform. Given the server's purpose (offensive security) and sibling tools that generate payloads, run attacks, and assess vulnerabilities, this likely executes security testing operations with high blast radius.

From the tool's own definition: "Tool named 'run_tool' with empty description on 'AI Powered penetration testing Platform for offensive security research' server alongside tools like 'ai_generate_attack_suite', 'aircrack_ng', and 'ai_vulnerability_assessment'."

## Use case

AI agents invoke run_tool to trigger actions in Nyxstrike. 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 Nyxstrike:

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

## Other tools on Nyxstrike (220)

- `clear_cache` — Destructive — https://policylayer.com/tools/nyxstrike/clear-cache.md
- `delete_file` — Destructive — https://policylayer.com/tools/nyxstrike/delete-file.md
- `wordlist_delete` — Destructive — https://policylayer.com/tools/nyxstrike/wordlist-delete.md
- `advanced_payload_generation` — Execute — https://policylayer.com/tools/nyxstrike/advanced-payload-generation.md
- `ai_generate_attack_suite` — Execute — https://policylayer.com/tools/nyxstrike/ai-generate-attack-suite.md
- `ai_generate_payload` — Execute — https://policylayer.com/tools/nyxstrike/ai-generate-payload.md
- `ai_reconnaissance_workflow` — Execute — https://policylayer.com/tools/nyxstrike/ai-reconnaissance-workflow.md
- `ai_test_payload` — Execute — https://policylayer.com/tools/nyxstrike/ai-test-payload.md
- `ai_vulnerability_assessment` — Execute — https://policylayer.com/tools/nyxstrike/ai-vulnerability-assessment.md
- `airbase_ng` — Execute — https://policylayer.com/tools/nyxstrike/airbase-ng.md
- `aircrack_ng` — Execute — https://policylayer.com/tools/nyxstrike/aircrack-ng.md
- `aircrack_ng_analysis` — Execute — https://policylayer.com/tools/nyxstrike/aircrack-ng-analysis.md
- `airdecap_ng` — Execute — https://policylayer.com/tools/nyxstrike/airdecap-ng.md
- `aireplay_ng` — Execute — https://policylayer.com/tools/nyxstrike/aireplay-ng.md
- `airmon_ng` — Execute — https://policylayer.com/tools/nyxstrike/airmon-ng.md
- `airodump_ng` — Execute — https://policylayer.com/tools/nyxstrike/airodump-ng.md
- `amass_scan` — Execute — https://policylayer.com/tools/nyxstrike/amass-scan.md
- `analyze_session` — Execute — https://policylayer.com/tools/nyxstrike/analyze-session.md
- `anew_data_processing` — Execute — https://policylayer.com/tools/nyxstrike/anew-data-processing.md
- `angr_symbolic_execution` — Execute — https://policylayer.com/tools/nyxstrike/angr-symbolic-execution.md
- `api_fuzzer` — Execute — https://policylayer.com/tools/nyxstrike/api-fuzzer.md
- `api_schema_analyzer` — Execute — https://policylayer.com/tools/nyxstrike/api-schema-analyzer.md
- `arjun_parameter_discovery` — Execute — https://policylayer.com/tools/nyxstrike/arjun-parameter-discovery.md
- `arjun_scan` — Execute — https://policylayer.com/tools/nyxstrike/arjun-scan.md
- `arp_scan_discovery` — Execute — https://policylayer.com/tools/nyxstrike/arp-scan-discovery.md
- `autopsy_analysis` — Execute — https://policylayer.com/tools/nyxstrike/autopsy-analysis.md
- `autorecon_comprehensive` — Execute — https://policylayer.com/tools/nyxstrike/autorecon-comprehensive.md
- `autorecon_scan` — Execute — https://policylayer.com/tools/nyxstrike/autorecon-scan.md
- `bbot_scan` — Execute — https://policylayer.com/tools/nyxstrike/bbot-scan.md
- `bettercap_wifi` — Execute — https://policylayer.com/tools/nyxstrike/bettercap-wifi.md
- …and 190 more: https://policylayer.com/tools/nyxstrike.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=nyxstrike · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/nyxstrike