mcpbeat Sign in

MemoryGuard MCP Server

local only

MemoryGuard runs on your own machine — the client starts it, so there is no endpoint to ping. 376 installs a week from pypi. Last commit 30 Sep 2026.

Local-first governed MCP memory backend for coding agents.

Installs per day peak 248 · avg 71 · +25% w/w
a month agotoday
376
Installs / week
pypi · agent-memguard
4
Stars
0 open issues
30 Sep 2026
Last commit
from GitHub
MIT
License
Python

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 19 September 2026. No other catalogue keeps this.

19 Sep the owner changed

What the code does

We read the source, 3 d ago · rules 995398eba69f

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a dangerous call memoryguard_audit.workspace → src/memoryguard/cli.py:1449, memoryguard_audit.workspace → src/memoryguard/cli.py:1289
        subprocess.Popen(
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.

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

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

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

Alternatives to MemoryGuard

same job, measured the same way
MemoryGuard
by merakosiris

Local-first governed MCP memory backend for coding agents.

local only
CP Memory
by cjhuochai

Local-first, governable long-term memory for AI coding agents

115 installs/wk local only
Agentos
by officialtanishsharma

Local-first persistent memory MCP server for AI coding agents.

local only
Dreamd
by botzrdev

Local-first, cross-harness memory for AI coding agents.

376 installs/wk local only
MCP Light Memory
by peterpirog

Local-first persistent memory for coding agents and MCP clients.

local only
PMB AI
by oleksiijko

Local-first persistent memory for AI coding agents.

278 installs/wk local only
Monet
by team-monet

Local-first, state-centric memory for coding agents. MCP server + CLI.

109 installs/wk local only
Context Engine
by shamsundarsk

Local-first persistent context memory MCP server for AI coding agents.

128 installs/wk local only

MemoryGuard — questions

Answers built from our own checks of this server.

Why is there no uptime for MemoryGuard?
MemoryGuard 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 agent-memguard was installed 376 times last week.
How do I connect MemoryGuard?
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 agent-memguard straight from pypi; nothing to host, nothing to sign up for.
How many people use MemoryGuard?
The pypi package agent-memguard was installed 376 times in the last week. Week over week that is +25%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is MemoryGuard open source?
Yes — it is published under the MIT licence, written in Python and 4 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.