Medium Risk

qflow_project_init

初始化项目的 qflow 配置。创建 .qflow/ 目录结构,包含配置文件和空任务列表。同时返回 onboardInfo 引导信息。

How to control qflow_project_init ↓

What qflow_project_init does on Qflow

AI agents use qflow_project_init 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_project_init needs a policy

This tool creates a new directory structure and configuration files for project initialization. While the changes are reversible (directories and files can be deleted), this is a write operation that modifies the project state. The severity is medium because incorrect initialization could require cleanup work, but the impact is localized to configuration and the action is reversible.

From the tool's definition Tool description states it '创建 .qflow/ 目录结构,包含配置文件和空任务列表' (creates .qflow/ directory structure, containing configuration files and empty task lists). This is explicitly a creation/initialization action that modifies the file system.

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

How to control qflow_project_init

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_project_init:

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

qflow_project_init 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_project_init

What does the qflow_project_init tool do? +

初始化项目的 qflow 配置。创建 .qflow/ 目录结构,包含配置文件和空任务列表。同时返回 onboardInfo 引导信息。. 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_project_init? +

Register the Qflow MCP server in PolicyLayer and add a rule for qflow_project_init: 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_project_init? +

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

Can I rate-limit qflow_project_init? +

Yes. Add a rate_limit block to the qflow_project_init 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_project_init completely? +

Set action: deny in the PolicyLayer policy for qflow_project_init. 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_project_init? +

qflow_project_init 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.