新手引导教程：init=初始化引导，step=获取当前步骤，complete=完成当前步骤，progress=查看进度，reset=重置引导，report=生成引导报告
AI agents call qflow_onboarding to retrieve information from Qflow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is an onboarding tutorial tool that manages guided walkthrough steps. While it has 'init' and 'reset' actions that modify state, and 'complete' that marks steps done, these are all low-impact state changes within a local project management context (no external systems, no data deletion, no code execution). The dominant operations are informational: getting steps, viewing progress, generating reports.
From the tool's definition 新手引导教程：init=初始化引导，step=获取当前步骤，complete=完成当前步骤，progress=查看进度，reset=重置引导，report=生成引导报告
Documented attack patterns abuse exactly the kind of access qflow_onboarding gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qflow, and nothing reaches the server without passing your rules. This is the rule we recommend for qflow_onboarding:
{
"version": "1",
"default": "deny",
"tools": {
"qflow_onboarding": {}
}
}qflow_onboarding is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
新手引导教程：init=初始化引导，step=获取当前步骤，complete=完成当前步骤，progress=查看进度，reset=重置引导，report=生成引导报告. It is categorised as a Read tool in the Qflow MCP Server, which means it retrieves data without modifying state.
Register the Qflow MCP server in PolicyLayer and add a rule for qflow_onboarding: 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 Qflow. Nothing to install.
qflow_onboarding is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the qflow_onboarding 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 qflow_onboarding. 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.
qflow_onboarding is provided by the Qflow MCP server (pangu-immortal/qflow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Qflow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
50 Qflow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.