john_crack
AI agents invoke john_crack to trigger actions in Kali Linux MCP Server. 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.
John the Ripper is a well-known password cracking tool. Even with an empty description, the tool name combined with the server's explicit mention of 'password cracking' capabilities makes it highly likely this tool executes password cracking operations. This falls under Execute (running external security tools) with critical severity given the potential for credential compromise and unauthorized access facilitation.
From the tool's definition Tool name 'john_crack' strongly implies John the Ripper password cracking tool; server description mentions 'password cracking' as an exposed capability on a penetration testing server
Attacks that exploit this kind of access
john_crack. It is categorised as a Execute tool in the Kali Linux MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali Linux MCP Server MCP server in PolicyLayer and add a rule for john_crack: 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 Linux MCP Server. Nothing to install.
john_crack 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 john_crack 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 john_crack. 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.
john_crack is provided by the Kali Linux MCP Server MCP server (ofryma/custom-mcp-library). 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 →