MemoCat — Shared AI Memory MCP Server

by montygovernance Your server? Claim it

local only

MemoCat — Shared AI Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 1 945 installs a week from pypi. Last commit 10 Sep 2026.

One shared, persistent memory across AI agents and systems, with semantic recall and live updates.

Installs per day peak 664 · avg 286

a month agotoday

1 945

Installs / week

pypi · memocat-mcp

Stars

1 open issues

10 Sep 2026

Last commit

0 releases in 90 days

MIT

License

Python

What the code does

We read the source, 17 h ago · rules 3dff92dd89df

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.

Runs an external command montycat_mcp/bootstrap.py:504

        completed = subprocess.run(  # noqa: S603 - our own verified binary

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.

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add memocat-mcp -- uvx memocat-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memocat-mcp": {
      "args": [
        "memocat-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.memocat-mcp]
command = "uvx"
args = ["memocat-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "memocat-mcp": {
      "args": [
        "memocat-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "memocat-mcp": {
      "args": [
        "memocat-mcp"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to MemoCat — Shared AI Memory

same job, measured the same way

Montycat MCP - Shared Memory for AI Agents

by montygovernance

Shared, persistent memory for AI agents, with semantic recall and live updates.

1 522 installs/wk local only

Central Intelligence

by alekseimarchenko

Persistent memory for AI agents. Store, recall, and share knowledge across sessions.

56 installs/wk local only

Creo Memories

by creo-memories

Memory system for AI agents with semantic search. Store and recall memories with ease.

answering

Goldhold

by jerrysrodz

Persistent memory for AI agents. Search, store, and recall across sessions.

54 installs/wk answering

Memory

by velixarai

Persistent memory for AI assistants. Store, search, and recall across sessions.

70 installs/wk local only

Iranti

by nfemmanuel

Persistent, shared memory for AI agents — facts, checkpoints, semantic search.

48 installs/wk local only

YourMemory

by sachitrafa

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

439 installs/wk local only

Kirok Memory

by tadfuji

Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation

64 installs/wk local only

MemoCat — Shared AI Memory — questions

Answers built from our own checks of this server.

Why is there no uptime for MemoCat — Shared AI Memory?

MemoCat — Shared AI Memory 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 memocat-mcp was installed 1 945 times last week.

How do I connect MemoCat — Shared AI Memory?

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 memocat-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use MemoCat — Shared AI Memory?

The pypi package memocat-mcp was installed 1 945 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 MemoCat — Shared AI Memory open source?

Yes — it is published under the MIT licence, written in Python, 45 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.