This record as markdown: /tools/hannes221-kali-mcp/container-stop.md
What container_stop does on Kali
AI agents call container_stop to permanently remove resources in Kali, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why container_stop is rated Critical
The tool explicitly removes the Docker container, which is an irreversible destructive action — any in-container state, running processes, and unsaved data are permanently lost. 'Remove' indicates the container is deleted, not merely paused. Combined with the server's ability to run tools like metasploit and sqlmap, misuse could terminate active security operations and lose all associated session data.
From the tool's definition Stop and remove the Kali Linux Docker container
Attacks that exploit this kind of access
The rule that runs container_stop safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Kali, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For container_stop, this is the rule to start with:
container_stop is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Kali, apply this rule, and every container_stop call is checked against it from then on.
Questions about container_stop
Stop and remove the Kali Linux Docker container. It is categorised as a Destructive tool in the Kali MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kali MCP server in PolicyLayer and add a rule for container_stop: 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.
container_stop is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the container_stop 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 container_stop. 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.
container_stop is provided by the Kali MCP server (hannes221/kali-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Kali, and thousands of servers like it.
Across the catalogue