DAG 工作流管理：start=启动工作流，advance=推进工作流，status=查看状态，list=列出所有工作流
AI agents invoke qflow_workflow 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 tool manages DAG (directed acyclic graph) workflows with operations to start and advance them. Starting and advancing workflows constitute executing external operations whose outcomes depend on the workflow configuration and input arguments. While some operations (status, list) are read-only, the primary risk comes from the ability to trigger workflow execution, making this Execute category.
From the tool's definition Tool description indicates: 'start=启动工作流' (start workflow), 'advance=推进工作流' (advance workflow), 'status=查看状态' (view status), 'list=列出所有工作流' (list all workflows).
Documented attack patterns abuse exactly the kind of access qflow_workflow 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_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"qflow_workflow": {
"limits": [
{
"counter": "qflow_workflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}qflow_workflow 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.
DAG 工作流管理：start=启动工作流，advance=推进工作流，status=查看状态，list=列出所有工作流. 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_workflow: 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_workflow 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_workflow 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_workflow. 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_workflow 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.