// SCAN REPORT

N3MemoryCore Lite (Working Memory)

7 tools. 3 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 1 Jul 2026

3 can modify or destroy data

4 read-only

7 tools total

Community server · catalogue entry verified 01/07/2026

How to control N3MemoryCore Lite (Working Memory) ↓

TOOL MAP

What N3MemoryCore Lite (Working Memory) exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous N3MemoryCore Lite (Working Memory) tools

Destructive · High delete_memories_by_session This tool permanently removes all memory records across multiple data structures within a session. Destructive · High delete_memory This tool permanently removes memory records from the working memory store. Write · Medium save_memory This tool creates or modifies memory entries in a vector+BM25 hybrid storage system backed by Redis Stack.

3 of N3MemoryCore Lite (Working Memory)'s 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control N3MemoryCore Lite (Working Memory)

PolicyLayer is an MCP gateway — it sits between your AI agents and N3MemoryCore Lite (Working Memory), and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_memories_by_session": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "save_memory": {
    "limits": [
      {
        "counter": "save_memory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_memories": {
    "limits": [
      {
        "counter": "list_memories_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register N3MemoryCore Lite (Working Memory) — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON N3MEMORYCORE LITE (WORKING MEMORY) →

Instant setup, no code required.

FULL CATALOGUE

All 7 N3MemoryCore Lite (Working Memory) tools

DESTRUCTIVE 2 tools

Destructive delete_memories_by_session Delete every memory (singles, parent docs, child chunks, sha guards) Destructive delete_memory Delete a memory by ID.

WRITE 1 tools

Write save_memory Save a memory entry (Lite: 7-day TTL).

READ 4 tools

Read list_memories List stored memories newest first. Read recall_thread §4.3.1 — Retrieve the memories sharing a turn_id plus N entries Read repair_memory Re-ensure the RediSearch index (idempotent). Read search_memory Hybrid (vector + BM25) search over stored memories.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about N3MemoryCore Lite (Working Memory)

Can an AI agent delete data through the N3MemoryCore Lite (Working Memory) MCP server? +

Yes. The N3MemoryCore Lite (Working Memory) server exposes 2 destructive tools including delete_memories_by_session, delete_memory. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through N3MemoryCore Lite (Working Memory)? +

The N3MemoryCore Lite (Working Memory) server has 1 write tools including save_memory. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach N3MemoryCore Lite (Working Memory).

How many tools does the N3MemoryCore Lite (Working Memory) MCP server expose? +

7 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on N3MemoryCore Lite (Working Memory)? +

Register the N3MemoryCore Lite (Working Memory) MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every N3MemoryCore Lite (Working Memory) tool call.

Deterministic rules across all 7 N3MemoryCore Lite (Working Memory) tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON N3MEMORYCORE LITE (WORKING MEMORY) →

Instant setup, no code required.

7 N3MemoryCore Lite (Working Memory) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.