Execute a shell command inside the Kali Linux container. Use this to run security tools like nmap, sqlmap, hydra, nikto, gobuster, john, hashcat, dirb, enum4linux, and any other installed tool.
AI agents invoke execute_command to trigger actions in Kali. 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.
This tool allows arbitrary shell command execution in a Kali Linux environment containing offensive security tools. While sandboxed in Docker, the effects depend entirely on agent arguments: commands could scan networks, exploit services, crack credentials, enumerate systems, or trigger destructive/financial actions depending on what the agent instructs it to do.
From the tool's definition Tool explicitly enables 'Execute a shell command inside the Kali Linux container' and lists powerful offensive security tools (nmap, sqlmap, hydra, nikto, gobuster, john, hashcat, dirb, enum4linux) that can scan systems, exploit vulnerabilities, crack…
Attacks that exploit this kind of access
Execute a shell command inside the Kali Linux container. Use this to run security tools like nmap, sqlmap, hydra, nikto, gobuster, john, hashcat, dirb, enum4linux, and any other installed tool. It is categorised as a Execute tool in the Kali MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali MCP server in PolicyLayer and add a rule for execute_command: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kali. Nothing to install.
execute_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_command rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for execute_command. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
execute_command is provided by the Kali MCP server (unaacceptable297/kali-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →