Mnemos MCP Server

If you already use Mnemos, the mnemos mcp server is the piece that lets your assistant work with it directly. Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.

What the server does

Claude Code is powerful, but it forgets your project context:

• Truly local-first — runs entirely on your machine. No network, no telemetry, no data leaves your project
• Zero dependencies — one self-contained, cgo-free Go binary. No Python, Docker, Qdrant, or Ollama
• Any MCP client — built for Claude Code, works with anything that speaks MCP
• Cited answers — every result links back to the exact file#section and line range, so claims are verifiable
• Fast search by default — SQLite FTS5 / bm25 out of the box; optional local semantic + hybrid search behind a build tag
• Read-write memory — the agent can capture durable notes (remember); you can manage the tree (forget, move, list)

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• Read — write memory**: the agent can capture durable notes (remember); you can manage the tree (forget, move, list)
• Retriever — Hit@1
• Hook — Matcher
• SessionStart — startup\
• UserPromptSubmit — recall cue phrases

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Where it fits

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Mnemos's toolset — Read, Retriever, Hook and 2 more — is a fair guide to whether it matches your workflow. It is maintained by arhuman; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.