@zensation/mcp

MCP memory server for ZenBrain: agent memory for any Model Context Protocol client — store, recall, consolidate, health. Local SQLite file, no account.

latest

Source

npm

Version: 0.1.6

Version published: 2 days ago

Weekly downloads: 45

Maintainers: 1

Weekly downloads

Created: 4 weeks ago

Source

@zensation/mcp

Status: early release. The tool surface is small on purpose and may still change before 1.0. The memory layers underneath it are the same ones the ZenBrain paper describes and the benchmarks measure.

An MCP server that gives any MCP client — Claude Desktop, Claude Code, Cursor, or your own — a memory that survives the conversation.

Four tools, one local SQLite file, no account and no network call.

Tool	What it does
`zenbrain_store`	Write something into long-term memory. Routing is automatic: a general statement becomes a semantic fact, a narrated event an episode, a sequence of instructions a procedure.
`zenbrain_recall`	Search every layer for what is relevant to a query. Results come back ranked, each tagged with the layer it came from.
`zenbrain_consolidate`	One sleep-like maintenance pass: promote repeated episodes into facts, decay stale slots, prune what fell below the retention threshold.
`zenbrain_health`	How full each layer is: slots in use, episodes, facts and how many are due for review, procedures, core blocks.

Install

Requires Node.js 22 or newer.

npm install -g @zensation/mcp

Configure your client

{
  "mcpServers": {
    "zenbrain": {
      "command": "npx",
      "args": ["-y", "@zensation/mcp"],
      "env": {
        "ZENBRAIN_DB": "~/.zenbrain/memory.db"
      }
    }
  }
}

Variable	Default	Meaning
`ZENBRAIN_DB`	`./zenbrain.db`	Path to the SQLite file. `:memory:` gives a store that is discarded when the process exits.
`ZENBRAIN_CONTEXTS`	`personal,work,learning,creative`	Comma-separated context domains for cross-context memory.

The server speaks MCP over stdio. Stdout carries protocol traffic only; diagnostics go to stderr.

The seven layers

Storing is not filing. Which layer a memory lands in decides how it decays, how it is retrieved, and whether it survives consolidation.

	Layer	Holds
7	Cross-Context Memory	Shared knowledge across domains
6	Core Memory	Pinned facts
5	Procedural Memory	"How to do X" — skills and workflows
4	Long-Term Semantic	Facts, with FSRS scheduling
3	Episodic Memory	Concrete experiences and events
2	Short-Term / Session	Current conversation context
1	Working Memory	Active task focus, 7±2 items

Each layer has its own retention, consolidation and retrieval rules. Review scheduling follows a forgetting curve rather than a fixed timer, and emotionally weighted content consolidates more strongly; both are implemented in @zensation/algorithms and can be read line by line.

This server configures no LLM provider, so nothing in it calls a model: routing on store is a content heuristic, and consolidation runs without generated summaries.

What this release does not do

Worth knowing before you wire it in:

No embedding provider is configured by default. Semantic search degrades to the non-vector path. Recall still works; it is less sharp than the benchmarked configuration. Pass an EmbeddingProvider through the library if you need that today.
SQLite similarity search is a full scan. Fine for one person's memory; use @zensation/adapter-postgres for larger volumes.
Consolidation is a tool call, not a schedule. Nothing runs it for you.
The store is a plain file. It is not encrypted. Put it somewhere you would put a notebook.

Using it as a library

The server factory is exported, so you can mount ZenBrain's tools on a server of your own or drive them in tests:

import { createZenBrainServer } from '@zensation/mcp/server';
import { MemoryCoordinator } from '@zensation/core';
import { SqliteAdapter } from '@zensation/adapter-sqlite';

const coordinator = new MemoryCoordinator({
  storage: new SqliteAdapter({ filename: './memory.db' }),
});

const server = createZenBrainServer(coordinator);
// connect it to any transport you like — the caller owns the coordinator's lifecycle

Zero-dependency, and where that stops

@zensation/algorithms and @zensation/core pull nothing but each other. That claim is checked in CI on every push against the packed tarballs, not against the source tree.

This package is deliberately outside that boundary. An MCP server needs the protocol SDK, so it carries one. Keeping it in its own package is what lets the core stay clean: installing @zensation/core never pulls the MCP SDK, and installing this never weakens the claim the core makes.

About ZenBrain

ZenBrain is a seven-layer, neuroscience-derived memory architecture for LLM agents, built as zero-dependency TypeScript and published under Apache-2.0. On LongMemEval-500 three of nine head-to-head answer-quality comparisons hold against Letta, Mem0 and A-Mem — all three against A-Mem, the remaining six are ties, none lost (three competitors x three LLM judges, Bonferroni-corrected, version-matched) — reaching 91.3% of a full-context oracle's binary-judge accuracy at 1/109.6 of the per-query token cost.