mcpbeat Sign in

Mnemo MCP Server

local only

Mnemo MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 3 037 installs a week from pypi. Last commit 17 Sep 2026.

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

Installs per day peak 1 048 · avg 347 · +27% w/w
a month agotoday
3 037
Installs / week
pypi · mnemo-mcp
11
Stars
1 open issues
17 Sep 2026
Last commit
0 releases in 90 days
Apache-2.0
License
Python

Nothing serious here today

Today is the operative word: we check Mnemo MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add mnemo-mcp -- uvx mnemo-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mnemo-mcp": {
      "args": [
        "mnemo-mcp"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mnemo-mcp]
command = "uvx"
args = ["mnemo-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "mnemo-mcp": {
      "args": [
        "mnemo-mcp"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mnemo-mcp": {
      "args": [
        "mnemo-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: API_KEYS (Provider API keys (format: PROVIDER_API_KEY:key,...). Select models per task with EMBEDDING_MODELS / RERANK_MODELS / LLM_MODELS (CSV provider/model, order = litellm fallback); provider is inferred from the model prefix. Empty embedding/rerank chains select Fastretrieval local ONNX/GGUF models; configured cloud chains never silently fall back to local.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Mnemo MCP

same job, measured the same way
Memento
by scrypster

Persistent memory for AI tools. Local-first knowledge graph with hybrid search.

local only
Memwright
by bolnet

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

108 installs/wk local only
Postgram
by ivo-toby

Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.

local only
Melchizedek
by louis49

Persistent memory for Claude Code — offline, single-file, hybrid search.

42 installs/wk local only
agentmem
by oxgeneral

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.

local only
Penfield Memory
by penfieldlabs

Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.

answering
Cozo Memory
by tobs-code

Local-first memory system for AI agents with hybrid search and graph reasoning

64 installs/wk local only
Inkwell
by veronchenko

Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links

local only

Mnemo MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Mnemo MCP?
Mnemo MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mnemo-mcp was installed 3 037 times last week.
How do I connect Mnemo MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mnemo-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Mnemo MCP?
The pypi package mnemo-mcp was installed 3 037 times in the last week. Week over week that is +27%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Mnemo MCP open source?
Yes — it is published under the Apache-2.0 licence, written in Python, 11 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.