learn

Server Claude Session Continuity leesgit/claude-session-continuity-mcp

Category Write

Risk class Medium

Parameters 00 required

WHAT IT DOES

What learn does on Claude Session Continuity

AI agents use learn 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 learn needs a policy

This tool writes/stores learned information (technical decisions, bug fixes, code patterns, dependency changes) to a session continuity store. It creates or modifies persistent context data reversibly. No code execution or deletion is implied.

From the tool's definition 자동 학습 (결정/수정/패턴/의존성) — stores different information based on type: decision, fix, pattern, dependency

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

learn Rate-limited

learn 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": {
    "learn": {
      "limits": [
        {
          "counter": "learn_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 learn

What does the learn tool do? +

자동 학습 (결정/수정/패턴/의존성). type에 따라 다른 정보 저장: - decision: 기술 결정 (alternatives 포함) - fix: 버그 수정 (solution, preventionTip) - pattern: 코드 패턴 (example, appliesTo) - dependency: 의존성 변경 (dependency, action, versions) 공통 필드: content, reason, files. 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 learn? +

Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for learn: 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 learn? +

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

Can I rate-limit learn? +

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

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

learn 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.