screen_learn_success · Screen Agent MCP: Risk & Policy

WHAT IT DOES

What screen_learn_success does on Screen Agent

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

WHY IT NEEDS A POLICY

Why screen_learn_success needs a policy

This tool writes/stores learned operation success data to a vector database and markdown files after user confirmation. It creates/updates persistent records but does not execute commands, delete data, or involve financial transactions. The blast radius is low as it only records UI interaction learning data.

From the tool's definition 记录学习内容到向量数据库和MD文件 (records learning content to vector database and MD files)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screen_learn_success Rate-limited

screen_learn_success 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "screen_learn_success": {
      "limits": [
        {
          "counter": "screen_learn_success_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Screen Agent, so you can run agents against it safely.

FAQ

Questions about screen_learn_success

What does the screen_learn_success tool do? +

用户确认操作成功后调用此工具，记录学习内容到向量数据库和MD文件。当用户说. It is categorised as a Write tool in the Screen Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on screen_learn_success? +

Register the Screen Agent MCP server in PolicyLayer and add a rule for screen_learn_success: 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 Screen Agent. Nothing to install.

What risk level is screen_learn_success? +

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

Can I rate-limit screen_learn_success? +

Yes. Add a rate_limit block to the screen_learn_success 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 screen_learn_success completely? +

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

screen_learn_success is provided by the Screen Agent MCP server (lqszhsp/screen-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.