MCP.Market

Mnemon MCP server

by nikitacometa·io.github.nikitacometa/mnemon-mcp·v1.0.1·3 stars
No reviews yet

Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
Growing

3 stars90 downloads/wk

Reviews

Write one

Nobody has reviewed Mnemon yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mnemon tools (7, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • memory_add

    Add a new memory to the persistent store. Supports 4 cognitive layers: episodic (events/sessions), semantic (facts/concepts), procedural (rules/workflows), resource (reference material). Automatically supersedes previous entries from the same source_file.

  • memory_deletewrite action

    Permanently delete a memory by ID. Cleans up superseding chain references: re-activates predecessor if one exists.

  • memory_export

    Export memories to JSON, Markdown, or claude-md (compact LLM-optimized) format. Supports filtering by layer, scope, date range. Returns the exported content as a string.

  • memory_health

    Diagnostic health report on the memory store. Returns expired entries, orphaned superseding chains, stale/never-accessed memories, low-confidence entries, and per-layer stats. Use cleanup=true to garbage-collect expired entries.

  • memory_inspect

    Inspect memory details or layer statistics. Without id: returns aggregate stats per layer (total, active, superseded, avg_confidence, top_entities). With id: returns the full memory row and optionally its history chain.

  • memory_search

    Full-text search across all memory layers using FTS5. Supports layer/entity/date/scope filtering. Returns scored results with snippets. Superseded entries excluded by default.

  • memory_updatewrite action

    Update an existing memory. Use supersede=true to create a versioned replacement (preserves history chain). Use supersede=false (default) to update fields in place.

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan51 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 72 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mnemon compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 47% of 802 Databases servers
Tools
7
the typical Databases server has 8
Tools that change things
29%
typical: 10%. Fewer write tools means less an agent can break
GitHub stars
3
more than 65% of 602 Databases servers
Downloads a week
90
more than 55% of 328 Databases servers with a package

What its tools let an agent do: 5 read · 2 change

Install Mnemon in Claude Code, Cursor or VS Code

Runs npx -y mnemon-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mnemon-mcp -- npx -y mnemon-mcp
Add to Cursor

What the publisher says

From the Mnemon repository's README, as published. We do not edit it. Read it on GitHub

mnemon-mcp

Persistent layered memory for AI agents. Local-first. Zero-cloud. Single SQLite file.

Landing Page · npm · GitHub

Your AI agent forgets everything after each session. Mnemon fixes that.

It gives any MCP-compatible client — OpenClaw, Claude Code, Cursor, Windsurf, or your own — a structured long-term memory backed by a single SQLite database on your machine. No API keys, no cloud, no telemetry. Just npm install and your agent remembers.

Why Layered Memory?

Flat key-value stores treat "what happened yesterday" the same as "never commit without tests." That's wrong — different kinds of knowledge have different lifetimes and access patterns.

Mnemon organizes memories into four layers:

A journal entry from last Tuesday and a coding rule that never changes live in different layers — because they should.

Retrieval Quality

Retrieval is measured against a 50-case golden set on a real 797-memory bilingual (RU/EN) corpus, through the actual MCP server — not a reimplementation. Current numbers (methodology & history):

Hybrid beats both legs individually, which is the whole argument for fusing them: lexical search has the better raw recall, vector search the better ranking, and RRF keeps both instead of averaging them away.

The eval doc tracks the failures too — score drift under corpus growth, the BM25 field-weight bug the eval caught, the two cases where fusion still loses to pure lexical search, and what the golden set does not cover. Numbers you can't audit are marketing; read how these are produced.

Architecture

flowchart LR
    C["MCP client<br/>Claude Code · Cursor · …"] -- "stdio / HTTP" --> T["10 tools · 4 resources · 3 prompts"]
    T --> R["retrieval pipeline<br/>FTS5 · vector · RRF fusion"]
    T --> M["memories + supersede chains"]
    I["KB import pipeline<br/>markdown → memories"] --> M
    M -- triggers --> F["FTS5 index (stemmed EN+RU)"]
    R --> F
    R --> V["sqlite-vec (optional, BYOK)"]

One SQLite file holds memories, the FTS5 index, and the optional vector index. Writes go through transactions that keep the supersede-chain invariant; reads run the staged retrieval pipeline described under Search.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Mnemon: common questions

Is Mnemon MCP server safe?
Mostly: it is graded B (78/100). Read the Mnemon safety report
How do I install Mnemon?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Mnemon need an API key?
Yes. The registry entry asks for MNEMON_EMBEDDING_API_KEY.
Is Mnemon maintained?
The last commit was 110 days ago (2026-07-17). The latest release is v1.0.1.
What can I use instead of Mnemon?
Servers from other publishers that do the same job: memo MCP server, open-memex MCP server and SAME - Stateless Agent Memory Engine MCP server. Compare all Mnemon alternatives.
How does Mnemon compare with other Databases MCP servers?
safety score 78/100 (higher than 47% of 802 Databases servers); tools 7 (the typical Databases server has 8); tools that change things 29% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Mnemon

Same job from other publishers: the closest match first, then the best rated.

All Mnemon alternatives →
  • memo
    Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
    A
  • open-memex
    Local-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.
    B
  • SAME - Stateless Agent Memory Engine
    Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
    B
  • hmem — Humanlike Memory for AI Agents
    Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
    A
  • LoreConvo
    Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
    B