save_prompt · Learnlog MCP: Risk & Policy

WHAT IT DOES

What save_prompt does on Learnlog

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

WHY IT NEEDS A POLICY

Why save_prompt needs a policy

This is a Write operation—it creates and persistently stores new data (user prompts and notes) in a local database without modification of existing records or irreversible deletion. Severity is medium because while data is stored permanently, the stored content is user educational metadata rather than critical system data, financial records, or system-level configurations.

From the tool's definition Tool name 'save_prompt' and description indicate it 'saves learning-related questions or notes' (Korean: '학습 관련 질문이나 메모를 저장합니다'). The function creates and stores new records of user prompts/notes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_prompt Rate-limited

save_prompt 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": {
    "save_prompt": {
      "limits": [
        {
          "counter": "save_prompt_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 Learnlog, so you can run agents against it safely.

FAQ

Questions about save_prompt

What does the save_prompt tool do? +

학습 관련 질문이나 메모를 저장합니다. 사용 방법: 1. 자동 저장: AI가 사용자의 학습 관련 질문을 인식하여 자동으로 저장 2. 수동 저장: 사용자가. It is categorised as a Write tool in the Learnlog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_prompt? +

Register the Learnlog MCP server in PolicyLayer and add a rule for save_prompt: 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 Learnlog. Nothing to install.

What risk level is save_prompt? +

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

Can I rate-limit save_prompt? +

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

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

save_prompt is provided by the Learnlog MCP server (yujaeyun/learnlog-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.