AI agents invoke ai_smart_continuation to trigger actions in Kali Security MCP. 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 operates within a Kali Linux penetration testing framework and appears to autonomously continue or execute the next steps in an attack/assessment workflow based on context. Given the sibling tools (execute_strategy, network_penetration, sqli_test, cmdi_test), 'continuing operations' in this context means triggering further offensive security actions.
From the tool's definition AI智能续接 - 基于当前上下文智能推荐下一步操作 (AI smart continuation - intelligently recommends and continues next operations based on current context); part of a penetration testing server with tools like adaptive_execute_strategy and adaptive_intelligent_orchestration
Documented attack patterns abuse exactly the kind of access ai_smart_continuation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kali Security MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ai_smart_continuation:
{
"version": "1",
"default": "deny",
"tools": {
"ai_smart_continuation": {
"limits": [
{
"counter": "ai_smart_continuation_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ai_smart_continuation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
AI智能续接 - 基于当前上下文智能推荐下一步操作. It is categorised as a Execute tool in the Kali Security MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali Security MCP server in PolicyLayer and add a rule for ai_smart_continuation: 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 Security MCP. Nothing to install.
ai_smart_continuation 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 ai_smart_continuation 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 ai_smart_continuation. 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.
ai_smart_continuation is provided by the Kali Security MCP server (seac-25/kali-security-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 249 Kali Security MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
249 Kali Security MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.