memory_learn · Jt MCP: Risk & Policy

WHAT IT DOES

What memory_learn does on Jt

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

WHY IT NEEDS A POLICY

Why memory_learn needs a policy

This tool creates or modifies data (knowledge storage) reversibly without destructive operations, code execution, or financial impact. Severity is medium because storing arbitrary knowledge could degrade system behavior if an AI agent stores malicious, false, or polluted data that influences future decisions.

From the tool's definition Tool name 'memory_learn' and description 'Store knowledge in a single call' indicate data creation/storage. The ability to 'Provide free-text and optionally an entity name' shows it creates or modifies persistent knowledge records.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_learn Rate-limited

memory_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": {
    "memory_learn": {
      "limits": [
        {
          "counter": "memory_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 Jt, so you can run agents against it safely.

FAQ

Questions about memory_learn

What does the memory_learn tool do? +

Store knowledge in a single call. Provide free-text and optionally an entity name. It is categorised as a Write tool in the Jt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memory_learn? +

Register the Jt MCP server in PolicyLayer and add a rule for memory_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 Jt. Nothing to install.

What risk level is memory_learn? +

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

Can I rate-limit memory_learn? +

Yes. Add a rate_limit block to the memory_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 memory_learn completely? +

Set action: deny in the PolicyLayer policy for memory_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 memory_learn? +

memory_learn is provided by the Jt MCP server (@houkasaurusrex/jt-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.