import_jsonl · mcp-Agentmemory MCP: Risk & Policy

WHAT IT DOES

What import_jsonl does on mcp-Agentmemory

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

WHY IT NEEDS A POLICY

Why import_jsonl needs a policy

This tool takes external session log files and writes new memory entries into the system. While it doesn't delete data (so not Destructive) or execute arbitrary code (so not Execute), it does persistently create and store data in the memory layer.

From the tool's definition Tool description states it 'creates memories' from imported JSONL data, which is a write operation that modifies the memory database. The verb 'creates' and the action of 'backfill memory' indicate data creation/insertion rather than retrieval or deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

import_jsonl Rate-limited

import_jsonl 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": {
    "import_jsonl": {
      "limits": [
        {
          "counter": "import_jsonl_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 mcp-Agentmemory, so you can run agents against it safely.

FAQ

Questions about import_jsonl

What does the import_jsonl tool do? +

Import a Claude Code / OpenCode / Codex JSONL session log. Parses user messages, applies heuristic category detection, and creates memories. Use this to backfill memory from past sessions. It is categorised as a Write tool in the mcp-Agentmemory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on import_jsonl? +

Register the mcp-Agentmemory MCP server in PolicyLayer and add a rule for import_jsonl: 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 mcp-Agentmemory. Nothing to install.

What risk level is import_jsonl? +

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

Can I rate-limit import_jsonl? +

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

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

import_jsonl is provided by the mcp-Agentmemory MCP server (obidel/agentmemory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.