合并记忆工具。action: flush(写入MEMORY.md)/load(读取MEMORY.md)。
AI agents use qflow_memory 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.
This tool performs both read and write operations on a MEMORY.md file. The 'flush' action writes data to the file, and 'load' retrieves it. While it includes a read component, the write capability (modifying MEMORY.md) is the more significant risk—an AI agent could overwrite memory state, affecting subsequent operations. This is reversible (not destructive), so Write is the appropriate category.
From the tool's definition Tool description states 'action: flush(写入MEMORY.md)/load(读取MEMORY.md)' where 写入 means 'write' and 读取 means 'read'. The flush action explicitly writes to MEMORY.md file.
Documented attack patterns abuse exactly the kind of access qflow_memory 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_memory:
{
"version": "1",
"default": "deny",
"tools": {
"qflow_memory": {
"limits": [
{
"counter": "qflow_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}qflow_memory 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.
Free to start. No card required.
合并记忆工具。action: flush(写入MEMORY.md)/load(读取MEMORY.md)。. 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.
Register the Qflow MCP server in PolicyLayer and add a rule for qflow_memory: 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_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the qflow_memory 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_memory. 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_memory 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.