Skip to main content
Glama
NeuralNexusNote

N3MemoryCore MCP — Lite (Ephemeral)

save_memory

Save memory entries with automatic deduplication and chunking of long content for verbatim recall. Memories expire after 7 days.

Instructions

Save a memory entry (Lite: 7-day TTL). Auto-deduplicates exact and near-duplicate content. Long content (>chunk_threshold chars) is chunked with a parent-document for verbatim recall.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYesMemory content to save.
agent_nameNoAgent display name (e.g. 'claude-code').
owner_idNoOwner UUID override (must match server config).
importanceNoImportance weight 0.5–2.0 (default 1.0).
session_idNoOptional project/task grouping key. Stored on the row and used as: (a) the ranking key for search_memory's b_session boost (match=1.0 / mismatch=0.6), and (b) the filter for delete_memories_by_session. Pass the same value across all calls for one project. Leave blank to use the server default (N3MC_SESSION_ID env var, or per-process UUIDv4).
turn_idNo§4.3.1 — Optional turn grouping label. Tag all memories saved within one conversation turn with the same turn_id. Enables recall_thread to surface the surrounding context later. Any non-empty string works; a short UUID, timestamp, or 'turn-N' format is recommended.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Discloses TTL ('Lite: 7-day TTL'), auto-deduplication, and chunking behavior. Lacks information on idempotency, overwrite behavior, or error handling, which would improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is three sentences with zero waste. First sentence states primary purpose, followed by concise coverage of key behaviors (TTL, dedup, chunking). Front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description could explain return values. It covers tool behavior (TTL, dedup, chunking) but lacks information on what is returned (e.g., memory ID, success status). Adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with detailed parameter descriptions. The tool description adds overall context (e.g., chunking, dedup) but does not significantly enhance parameter meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Save a memory entry' with specific verb and resource. It distinguishes from sibling tools (delete, list, recall, repair, search) by focusing on creation/insertion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description does not explicitly state when to use this tool versus alternatives. It implies usage for saving memories but lacks when-not or alternative context. Sibling tool names suggest distinct purposes, but no guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/NeuralNexusNote/n3mcmcp-lite'

If you have feedback or need assistance with the MCP directory API, please join our Discord server