Medium Risk

qflow_profile_switch

切换到指定的 Profile 预设(自动应用 mode 和 contextModules)。

How to control qflow_profile_switch ↓

What qflow_profile_switch does on Qflow

AI agents use qflow_profile_switch to create or update resources in Qflow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qflow environment.

Medium Risk

Why qflow_profile_switch needs a policy

This tool creates or modifies configuration state by switching to a profile preset and automatically applying mode and context modules. These are reversible changes to application settings rather than destructive operations, and do not involve reading data, executing arbitrary code, or financial transactions. The action is Write-category as it persistently modifies the tool's operational state/configuration.

From the tool's definition Tool name 'qflow_profile_switch' and description '切换到指定的 Profile 预设(自动应用 mode 和 contextModules)' (Switch to a specified Profile preset and automatically apply mode and contextModules) indicates modifying application state/configuration by switching profiles…

Documented attack patterns abuse exactly the kind of access qflow_profile_switch gives an agent:

How to control qflow_profile_switch

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_profile_switch:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "qflow_profile_switch": {
      "limits": [
        {
          "counter": "qflow_profile_switch_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

qflow_profile_switch stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Qflow — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about qflow_profile_switch

What does the qflow_profile_switch tool do? +

切换到指定的 Profile 预设(自动应用 mode 和 contextModules)。. It is categorised as a Write tool in the Qflow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on qflow_profile_switch? +

Register the Qflow MCP server in PolicyLayer and add a rule for qflow_profile_switch: 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.

What risk level is qflow_profile_switch? +

qflow_profile_switch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit qflow_profile_switch? +

Yes. Add a rate_limit block to the qflow_profile_switch 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.

How do I block qflow_profile_switch completely? +

Set action: deny in the PolicyLayer policy for qflow_profile_switch. 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.

What MCP server provides qflow_profile_switch? +

qflow_profile_switch 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.

Enforce policy on every Qflow tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.