auto_learn_decision · Claude Session Continuity MCP

WHAT IT DOES

What auto_learn_decision does on Claude Session Continuity

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

WHY IT NEEDS A POLICY

Why auto_learn_decision needs a policy

This tool writes/creates records of architectural and technical decisions into persistent session memory. It creates new data (decision logs) that can be referenced later. This is a Write operation — it stores decision metadata reversibly (a sibling tool 'delete_memory' exists, implying records can be removed).

From the tool's definition 아키텍처/기술 결정 사항을 자동 기록합니다 (automatically records architecture/technology decisions); 왜 이 선택을 했는지 기록하여 나중에 참조할 수 있습니다 (records why this choice was made for later reference)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

auto_learn_decision Rate-limited

auto_learn_decision 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": {
    "auto_learn_decision": {
      "limits": [
        {
          "counter": "auto_learn_decision_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 Claude Session Continuity, so you can run agents against it safely.

FAQ

Questions about auto_learn_decision

What does the auto_learn_decision tool do? +

아키텍처/기술 결정 사항을 자동 기록합니다. 왜 이 선택을 했는지 기록하여 나중에 참조할 수 있습니다. It is categorised as a Write tool in the Claude Session Continuity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on auto_learn_decision? +

Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for auto_learn_decision: 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 Claude Session Continuity. Nothing to install.

What risk level is auto_learn_decision? +

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

Can I rate-limit auto_learn_decision? +

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

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

auto_learn_decision is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.