合并自动驾驶工具。action: config(配置)/start(启动)/pause(暂停)/resume(恢复)/status(状态)/stop(停止)/step(单步)/commit(提交)/loop_start(启动循环)/loop_stop(停止循环)/loop_status(循环状态)。
AI agents invoke qflow_autopilot 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.
This autopilot tool controls execution of automated processes with multiple operational commands (start, pause, resume, step, loop control). While individual status/config queries might be Read operations, the dominant functionality involves triggering and managing autonomous execution of workflows.
From the tool's definition Tool provides actions to 'start(启动)', 'pause(暂停)', 'resume(恢复)', 'stop(停止)', 'step(单步)', 'commit(提交)', and 'loop_start(启动循环)' — these are operational triggers that execute automated workflows and process state changes.
Documented attack patterns abuse exactly the kind of access qflow_autopilot 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_autopilot:
{
"version": "1",
"default": "deny",
"tools": {
"qflow_autopilot": {
"limits": [
{
"counter": "qflow_autopilot_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}qflow_autopilot 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.
合并自动驾驶工具。action: config(配置)/start(启动)/pause(暂停)/resume(恢复)/status(状态)/stop(停止)/step(单步)/commit(提交)/loop_start(启动循环)/loop_stop(停止循环)/loop_status(循环状态)。. 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_autopilot: 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_autopilot 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_autopilot 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_autopilot. 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_autopilot 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.