MemoCat - Shared AI Memory MCP Server

A self-hosted MCP server that gives AI agents persistent, searchable memory. Claude, Codex, Cursor, and any Model Context Protocol client write to one memory and read each other's. It runs locally over stdio via the published package.

People who work with agent memory, codex and embeddings and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-17 · ★ 54 · #24 OF 304 MAINTAINED MEMORY · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install MemoCat - Shared AI Memory

before you install - you'll need

Set MONTYCAT_URI, MONTYCAT_SUPEROWNER, MONTYCAT_PASSWORD before connecting. MONTYCAT_TLS is optional or environment-specific per the README.

Claude Code

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

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · container (OCI image) - can be sandboxed away from your filesystem

repo age created 2026-07-20 - young repo, little track record yet

license MIT - declared in the repository

pypi package memocat-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.MontyGovernance is GitHub-verified and matches the repo owner

03 · What MemoCat - Shared AI Memory can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v1.1.4 · 2026-09-10

1.1.4 - 2026-09-11 · Maintenance release. No tool, API, or engine-compatibility changes. · Changed · Refresh the 512×512 transparent directory icon carried by the Claude Desktop · extension, the Claude plugins, and the…

v1.1.3 · 2026-09-09

1.1.3 - 2026-09-08 · Changed · Add timestamp_field to montycat_semantic_search. since and until · now build native SDK Timestamp filters against the selected Timestamp index · field, defaulting to _created_at for…

v1.1.2 · 2026-09-07

1.1.2 - 2026-09-06 · Improves the product identity advertised to MCP clients. · Changed · Advertise Montycat MCP as the human-facing server name during the MCP handshake while retaining existing package IDs and Claude…

04 · Who maintains MemoCat - Shared AI Memory

MemoCat - Shared AI Memory is maintained by montygovernance. We track 2 MCP servers from montygovernance - 2 actively maintained, 108 combined GitHub stars, oldest repo from Jul 2026. Full record: all servers from montygovernance.

Montycat MCP - Shared Memory for AI Agents Shared, persistent memory for AI agents, with semantic recall and live updates. ★ 54

05 · Facts

repository: github.com/montygovernance/memocat-mcp
category: memory - ranked #24 of 304 actively-maintained memory servers as of 2026-09-18.
release cadence: 10+ releases in the last 90 days (latest 2026-09-10)
registry: io.github.MontyGovernance/memocat-mcp (active, first published 2026-08-28 · 2 versions)
packages: pypi:memocat-mcp · oci:docker.io/montygovernance/memocat-mcp:0.4.3

06 · MemoCat - Shared AI Memory FAQ

What is MemoCat - Shared AI Memory?

Is MemoCat - Shared AI Memory still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-17 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install MemoCat - Shared AI Memory?

Run `uvx memocat-mcp`. The README documents 4 environment variables (MONTYCAT_URI, MONTYCAT_TLS, MONTYCAT_SUPEROWNER…) to set first. Set MONTYCAT_URI, MONTYCAT_SUPEROWNER, MONTYCAT_PASSWORD before connecting. MONTYCAT_TLS is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does MemoCat - Shared AI Memory run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to MemoCat - Shared AI Memory

Alternatives to MemoCat - Shared AI Memory

Maintained memory servers if MemoCat - Shared AI Memory isn't the fit.

Pairs well with

Servers that cover what MemoCat - Shared AI Memory doesn't - only shown when the pairing reason fits the companion.

More memory MCP servers · Montycat MCP - Shared Memory for AI Agents · Brain - The Recorder · Engram Cc · Open Zk Kb · Chat Recall

More Python MCP servers · Flameox · Jacobian · Server Motherduck · see all