Mnema MCP server
ai.zimac/mnema·v0.2.0Local-first, formally verified memory for AI agents: consult/learn/related/list over MCP.
0 stars
Reviews
Write oneNobody has reviewed Mnema yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Mnema tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- –Code scanpackage could not be scannedn/a
- –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 76 days ago12/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
How Mnema compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 60/100
- higher than 15% of 48,255 servers
Install Mnema in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the Mnema repository's README, as published. We do not edit it. Read it on GitHub
Mnema
Local-first, formally verified memory for AI agents — one shared store, every client, over MCP.
Your agents rent their intelligence from a lab; their memory should be yours. Mnema is a single, durable store of what your agents have learned — consult it before you act, learn a durable fact, walk the related graph, list what's recent. Data lives in ~/.mnema on your machine and nothing leaves it unless you point it somewhere.
machine-checked (property catalog discharged by 250+ tests, an exhaustive CRDT conformance model checker, Kani proofs, and a TLA⁺ model). Every released binary passed that gate on its exact commit.
- Verified engine. The embedded engram database is formally specified and
no account.
- Local-first. An open, append-only segment format in ~/.mnema. No cloud,
and your CI all talk to the same memory. Recall is lexical + graph spreading-activation (plus optional semantic embeddings), with an honest confidence band on every answer.
- One store, every client. Claude Code, Claude Desktop, Cursor, your scripts,
This repository hosts the public release bundles (.mcpb) and prebuilt
binaries. The product, docs, and downloads live at mnema.zimac.ai.
Install
From the MCP Registry (recommended)
Mnema is published to the official MCP Registry as ai.zimac/mnema. Any registry-aware client can install it by name; it pulls the platform .mcpb bundle from this repo's releases and verifies its fileSha256.
.mcpb bundle (manual)
Grab the bundle for your platform from the latest release and open it with an MCP-bundle-aware client (e.g. Claude Desktop → Extensions):
A .mcpb is a ZIP of a manifest.json, the mnema binary, and this README. Each is dry-run verified (the bundled binary completes an MCP initialize handshake) before release.
Headless binary (curl | sh)
For agents, scripts, and CI — installs the standalone mnema binary:
curl -fsSL https://mnema.zimac.ai/install.sh | sh(macOS universal + Linux x8664 prebuilt; anything else builds from source. The macOS GUI app** is a separate download at mnema.zimac.ai.)
Give your agents memory
claude mcp add mnema -- mnema mcpThat's the whole setup: mnema mcp auto-starts the shared local store if it isn't running, and the session gets four tools — consult (search before you act), learn (record a durable fact), related (graph neighbours), list (browse). Any MCP client works; the generic config is:
{ "mcpServers": { "mnema": { "command": "mnema", "args": ["mcp"] } } }Point it at a shared / team store
The same binary bridges to a remote Mnema (a token-protected mnema serve or a hosted learnings pod) instead of the local one:
MNEMA_URL=https://memory.example.com MNEMA_TOKEN=<secret> mnema mcpWith a non-loopback URL nothing is auto-started — it's a pure authenticated bridge.
Configuration
Links
- Product & downloads: https://mnema.zimac.ai
- Registry entry: ai.zimac/mnema on https://registry.modelcontextprotocol.io
- Releases (.mcpb + binaries): https://github.com/Zimac-AI/mnema/releases
Mnema is a Zimac project.
Nothing above is checked by us. What we check is on the safety report.
Mnema: common questions
- Is Mnema MCP server safe?
- With care: it is graded C, so read the findings first (60/100). Read the Mnema safety report
- Does Mnema need an API key?
- Yes. The registry entry asks for
MNEMA_TOKEN. - Is Mnema maintained?
- The last commit was 115 days ago (2026-07-12). The latest release is v0.2.0.
- What can I use instead of Mnema?
- Servers from other publishers that do the same job: Deja Vu MCP server, Memorix MCP server and Nautilus Compass Memory MCP server.
Alternatives to Mnema
Same job from other publishers: the closest match first, then the best rated.
- Deja Vudeja-vu: local memory over the session histories of forty-three coding agents.not reviewedEstablishedA
MemorixLocal-first project memory with legacy MCP and 2026 discovery compatibility.not reviewedEstablishedB- Nautilus Compass MemoryLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.not reviewedEstablishedB