敏捷工作流预设：list=列出所有阶段，get=获取指定阶段，step=执行步骤
AI agents invoke qflow_agile to trigger actions in Qflow. 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.
The tool supports listing and getting workflow phases (Read-like), but also 'step=执行步骤' which means 'execute steps', implying it can trigger workflow execution actions. The most severe applicable category is Execute. Confidence is moderate because the description is brief and in Chinese, leaving the exact side-effects of 'execute steps' somewhat ambiguous.
From the tool's definition step=执行步骤 (execute steps), get=获取指定阶段 (get specified phase), list=列出所有阶段 (list all phases) — the tool manages agile workflow phases including executing steps
Documented attack patterns abuse exactly the kind of access qflow_agile 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_agile:
{
"version": "1",
"default": "deny",
"tools": {
"qflow_agile": {
"limits": [
{
"counter": "qflow_agile_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}qflow_agile 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.
敏捷工作流预设：list=列出所有阶段，get=获取指定阶段，step=执行步骤. It is categorised as a Execute tool in the Qflow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Qflow MCP server in PolicyLayer and add a rule for qflow_agile: 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_agile 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 qflow_agile 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_agile. 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_agile 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.