Memshelf MCP Server

by ignatenkofi Your server? Claim it

local only

Memshelf MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 80 installs a week from pypi. Last commit 14 Sep 2026.

Working memory for AI agents: digest-indexed episodes on a git shelf, recalled a section at a time.

Installs per day peak 23 · avg 12 · -10% w/w

a month agotoday

Installs / week

pypi · memshelf-mcp

Stars

0 open issues

14 Sep 2026

Last commit

0 releases in 90 days

MIT

License

Python

What the code does

We read the source, 3 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 src/memshelf_mcp/core/init.py:116, src/memshelf_mcp/core/remote.py:53, [пакет] src/memshelf_mcp/core/init.py:116 и ещё 13

    return subprocess.run(["git", "-C", str(root), *args], capture_output=True, text=True)

Dumps the whole environment adapters/claude-desktop/try_bundle.py:133

    environment = dict(os.environ)

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 memshelf-mcp -- uvx memshelf-mcp

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

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

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

Alternatives to Memshelf MCP

same job, measured the same way

Repo Memory

by yubinkim444

Shared, git-tracked working memory for AI agents on the same codebase.

99 installs/wk local only

Prism Coder

by dcostenco

Session memory for coding agents: local-first recall, drift detection, on-device inference.

2 167 installs/wk local only

Nexusmem

by yaminbkk

Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.

88 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

Verbative Memory

by verbative

On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.

366 installs/wk local only

Attestari

by attestari

Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.

146 installs/wk local only

AgentCommons.me

by ivgolovach

Public working memory for AI agents: messages, shared pages, and resumable tasks.

local only

Bluecolumn Memory

by bluecolumnconsulting-lgtm

Persistent memory for AI agents — audio intelligence + Music Memory ingestion and recall

52 installs/wk local only

Memshelf MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Memshelf MCP?

Memshelf 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 memshelf-mcp was installed 80 times last week.

How do I connect Memshelf 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 memshelf-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Memshelf MCP?

The pypi package memshelf-mcp was installed 80 times in the last week. Week over week that is -10%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Memshelf MCP open source?

Yes — it is published under the MIT licence, written in Python and 0 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.