mcpbeat Sign in

Mnemolith MCP Server

local only

Mnemolith runs on your own machine — the client starts it, so there is no endpoint to ping. 1 129 installs a week from pypi. Last commit 24 Oct 2026.

Shared local memory for AI coding tools that stays true to your code.

Installs per day peak 361 · avg 37
a month agotoday
1 129
Installs / week
pypi · mnemolith
3
Stars
0 open issues
24 Oct 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 2 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

    return subprocess.run([shutil.which("claude") or "claude", *args], capture_output=True, text=True, timeout=60)
  svg.innerHTML = paths[name];

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

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 mnemolith -- uvx mnemolith
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mnemolith": {
      "command": "uvx",
      "args": [
        "mnemolith"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.mnemolith]
command = "uvx"
args = ["mnemolith"]
.cursor/mcp.json
{
  "mcpServers": {
    "mnemolith": {
      "command": "uvx",
      "args": [
        "mnemolith"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mnemolith": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mnemolith"
      ]
    }
  }
}

Alternatives to Mnemolith

same job, measured the same way
Aether Cache
by anishchugh05

Shared local memory for AI coding tools that stays true to your code.

2 967 installs/wk local only
TeamShared
by xhad

Shared memory for coding agents. Stop re-explaining your codebase every session.

92 tools answering
Kijito
by kijito

Shared memory and mail for your AI agents. Verified with Claude Code; other MCP clients in testing.

answering
Topos
by krv-labs

Structural code-quality tools for AI coding agents.

1 617 installs/wk local only
Th Memory MCP
by worakorn-prince

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

511 installs/wk local only
ASR Memory (에사 AI) — Shared memory for AI tools
by asrmemory

Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.

answering
Graphmem
by sonic182

Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.

283 installs/wk local only
Campfyrr
by sarkars

Campfyrr, shared team memory for Claude Code

answering

Mnemolith — questions

Answers built from our own checks of this server.

Why is there no uptime for Mnemolith?
Mnemolith 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 mnemolith was installed 1 129 times last week.
How do I connect Mnemolith?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls mnemolith straight from pypi; nothing to host, nothing to sign up for.
How many people use Mnemolith?
The pypi package mnemolith was installed 1 129 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Mnemolith open source?
Yes — it is published under the MIT licence, written in Python and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.