Loading ToolBench
A Model Context Protocol (MCP) server that wraps the aircrack-ng suite for WiFi security testing. Provides tools for network interface management, WiFi scanning, handshake capture, packet injection, and WPA/WEP key cracking.
This server has severe definition quality gaps. Of 17 tools, only 9 have complete input schemas with typed properties and descriptions. Descriptions vary: tools 1-9 are detailed (100-200 chars, actionable); tools 10-17 are bare stubs (10-30 chars, no context). No tool documents output schema. No error handling guidance. No parameter validation rules stated. Security-critical tools (deauth, fake_auth, create_evil_twin) lack permission gates or confirmation patterns.
ARP request replay attack (WEP IV generation)
Automatically crack WEP networks
Capture WPA/WPA2 handshake for a specific BSSID using airodump-ng. Writes capture to the specified output file.
Check a capture file for a valid captured WPA handshake using aircrack-ng (run without a wordlist). Reports how many handshakes were found.
Check whether an interface is in managed or monitor mode using iwconfig. If no interface is given, shows all wireless interfaces.
Clean capture files for faster cracking
Crack WPA/WEP key using a wordlist
8 of 17 tools (47%) have empty or missing input schemas. Tools crack_wifi, list_interfaces, fake_auth, arp_replay, decrypt_capture, create_evil_twin, auto_crack_wep, clean_capture show only '{}' or no properties.
8 tools have descriptions under 20 characters ('Crack WPA/WEP key using a wordlist' is 35 chars, but 'Fake authentication attack (WEP)' is 31 chars; however, 'Decrypt captured packets with known key' is 40 chars). Tools 10-17 lack context for when/why to call them.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | <=2025-11-25 | v2 |
Create a fake access point
Send deauthentication packets to a target using aireplay-ng. Used to force clients to reconnect so a handshake can be captured.
Decrypt captured packets with known key
Fake authentication attack (WEP)
Run 'airmon-ng check kill' to stop background processes (e.g. NetworkManager, wpa_supplicant) that commonly interfere with enabling monitor mode.
List all network interfaces and their status using ifconfig. Equivalent to running 'ifconfig' (falls back to 'ip addr' if unavailable).
List available wireless interfaces (airmon-ng)
Scan nearby WiFi networks using airodump-ng. Runs for a limited time (default 30s) then returns results. Optionally lock onto a single channel or BSSID, or scan a specific band.
Enable monitor mode on a wireless interface using airmon-ng. Returns the name of the monitor interface created.
Disable monitor mode on an interface using airmon-ng.
No tool documents its output schema. LLMs cannot infer what fields to expect or plan downstream calls. E.g., scan_wifi returns results but structure is undocumented; capture_handshake writes a file but success/failure format is unclear.
Destructive/sensitive tools (deauth, fake_auth, arp_replay, create_evil_twin) lack permission gates, confirmation patterns, or dry-run support. An agent could invoke 'deauth' without authorization checks or user confirmation, risking network disruption.
No error handling guidance. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next. E.g., if scan_wifi times out or capture_handshake fails, the agent has no recovery path.