mnemo-mcp CLAUDE.md

mnemo-mcp CLAUDE.md is an instructions file for Claude Code from Skye-flyhigh/mnemo-mcp. It costs 834 tokens per session, scanned A, original, MIT.

A set of project instructions for mnemo-mcp, a standalone MCP server that gives compatible AI agents persistent, associative memory stored locally. MCP is a standard way for AI tools to connect to services.

In plain words
What is it for?
It helps developers install, build, run, configure, and inspect mnemo-mcp, including its embedding provider and SQLite memory database.
Why use it?
It documents how to build and run the server and how its memory can fade unless it is reinforced.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/skye-flyhigh/mnemo-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/Skye-flyhigh/mnemo-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mnemo-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/skye-flyhigh/mnemo-mcp/claude-md.svg)](https://agentmods.dev/instructions/skye-flyhigh/mnemo-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/skye-flyhigh/mnemo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/skye-flyhigh/mnemo-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 834 This file is loaded in full into every session.
When invoked 834 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00834 $0.00834
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 5d ago against content hash 1d549bf0892a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mnemo-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mnemo-mcp

What is mnemo-mcp

A standalone MCP server that provides persistent, decaying, associative memory to any MCP-compatible AI agent. Local-first, pluggable embeddings, zero mandatory cloud dependency.

Key differentiator

Cognitive decay. Memories fade unless reinforced. Core memories persist. This isn't a flat database — it's a portable hippocampus.

Quick Reference

Build & Run

npm install          # Install dependencies
npm run build        # Compile TypeScript
npm start            # Run the MCP server (stdio)
npm run dev          # Watch mode

Test with MCP Inspector

npx @modelcontextprotocol/inspector node dist/index.js

Environment Variables

MNEMO_EMBEDDING_PROVIDER=ollama          # ollama (default) or openai
MNEMO_EMBEDDING_MODEL=nomic-embed-text   # Model name (provider-aware defaults)
MNEMO_EMBEDDING_BASE_URL=                # API base URL (provider-aware defaults)
MNEMO_EMBEDDING_API_KEY=                 # Required for openai provider
MNEMO_DIMENSIONS=768                     # Embedding dimensions
MNEMO_DB_PATH=~/.mnemo/memory.db         # SQLite database path

Architecture

src/
  index.ts        # MCP server entry (stdio transport, 6 tools)
  store.ts        # VectorStore (better-sqlite3 + sqlite-vec)
  embeddings.ts   # Embedding providers (Ollama + OpenAI-compatible) + factory
  memory.ts       # Memory manager (add, search, delete, bump, decay)
  types.ts        # Types, interfaces, constants, config
  utils.ts        # Hash, ID generation helpers

MCP Tools

Tool Description
remember Store a memory with tag, categories, namespace
remember_batch Store multiple memories in one call (batch embedding)
recall Semantic search by query (default 10 results)
forget Delete a memory by ID
update Patch content or metadata of an existing memory
bump Reinforce a memory's weight
decay Trigger decay cycle (tag-based weight reduction)
inspect View a specific memory or aggregate stats

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 83 lines · 834 tokens per session scan A 1d549bf0892a

Subscribe to this mod's changes

mnemo-mcp CLAUDE.md is an instructions file published in the GitHub repository Skye-flyhigh/mnemo-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 834 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.