MCPgee
MCPgee
MCPgeeMCPgee

MCP Memory Keeper

v0.12.2•Knowledge & Memory•stable

Provides persistent context management for Claude AI coding assistants, allowing you to save and restore conversation context, create checkpoints, and organize information across sessions to prevent losing important work history and decisions during

ai-assistantclaude-aiclaude-codecontext-managementcontext-persistence
Share:
122
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is MCP Memory Keeper?

MCP Memory Keeper is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides persistent context management for claude ai coding assistants, allowing you to save and restore conversation context, create checkpoints, and organize information across sessions to prevent l...

Provides persistent context management for Claude AI coding assistants, allowing you to save and restore conversation context, create checkpoints, and organize information across sessions to prevent losing important work history and decisions during

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Provides persistent context management for Claude AI coding

Use Cases

Persistent conversation context
Session checkpoint management
Work history preservation
mkreyman

Maintainer

LicenseMIT License
Languagetypescript
Versionv0.12.2
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y mcp-memory-keeper

Manual Installation

npx -y mcp-memory-keeper

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Memory Keeper

MCP Memory Keeper is a persistent context management server for Claude AI coding assistants, solving the problem of losing work history and decisions when the Claude conversation window fills up and compacts. It provides a SQLite-backed memory layer with 38 tools covering session management, context saving and retrieval, full-text and semantic search, checkpoint snapshots, batch operations, git integration, and multi-agent context sharing. Developers use it to maintain continuity across long coding sessions — saving architectural decisions, task progress, and file states as checkpoints, then restoring them in fresh sessions without missing a beat.

Prerequisites

  • Node.js 18+ and npm installed
  • Claude Code or Claude Desktop as the MCP client
  • No external API keys required — all storage is local SQLite
  • Git (optional, enables automatic context correlation with branches and commits)
  • Write access to ~/mcp-data/memory-keeper/ for database storage (configurable via DATA_DIR)
1

Add Memory Keeper to Claude Code with one command

The recommended installation runs Memory Keeper via npx and registers it with the Claude Code MCP manager in a single command. Context is stored in ~/mcp-data/memory-keeper/ automatically.

claude mcp add memory-keeper npx mcp-memory-keeper
2

Or add to Claude Desktop via config file

For Claude Desktop, add the server entry to your claude_desktop_config.json manually.

{
  "mcpServers": {
    "memory-keeper": {
      "command": "npx",
      "args": ["mcp-memory-keeper"]
    }
  }
}
3

Configure optional environment variables

Customize storage location, token limits, and the tool profile. The 'standard' profile exposes 22 tools for daily use; 'full' loads all 38. Set these in the MCP config env block.

{
  "mcpServers": {
    "memory-keeper": {
      "command": "npx",
      "args": ["mcp-memory-keeper"],
      "env": {
        "DATA_DIR": "/home/user/mcp-data/memory-keeper/",
        "TOOL_PROFILE": "standard",
        "MCP_MAX_TOKENS": "25000"
      }
    }
  }
}
4

Start a session at the beginning of each work session

Ask Claude to start a Memory Keeper session at the beginning of a coding session. This initialises git tracking and sets the default channel for all subsequent saves.

5

Save important context and create checkpoints

As you work, ask Claude to save decisions, progress, and file states. Before the context window fills, ask Claude to create a named checkpoint so you can restore it in a new session.

MCP Memory Keeper Examples

Client configuration

Example claude_desktop_config.json for MCP Memory Keeper with standard tool profile and custom data directory.

{
  "mcpServers": {
    "memory-keeper": {
      "command": "npx",
      "args": ["mcp-memory-keeper"],
      "env": {
        "DATA_DIR": "/home/user/mcp-data/memory-keeper/",
        "TOOL_PROFILE": "standard"
      }
    }
  }
}

Prompts to try

Example prompts for managing context across long coding sessions with Memory Keeper's 38 tools.

- "Start a memory-keeper session for the auth-service project"
- "Save this architectural decision: we are using JWT with 24h refresh tokens"
- "Search memory-keeper for everything saved about the database schema"
- "Create a checkpoint called 'before-refactor' with a description of the current state"
- "Restore from the checkpoint named 'before-refactor' and summarise what we were working on"

Troubleshooting MCP Memory Keeper

Context saved in one session is not visible in a new Claude session

Ensure you are starting the new session with 'mcp_context_session_start' and specifying the same channel or project directory as the previous session. Memory Keeper scopes context to channels — mismatched channels will make prior saves invisible.

npx mcp-memory-keeper fails with native module errors on macOS/Linux

The server uses SQLite via better-sqlite3 which includes a native addon. If npx fails, install globally instead: 'npm install -g mcp-memory-keeper' then update the config command to 'mcp-memory-keeper'.

Responses are truncated or items are missing from retrieval results

The default MCP_MAX_TOKENS is 25000. If your client supports larger responses, increase it. Alternatively lower MCP_MAX_ITEMS or use pagination parameters (limit/offset) in mcp_context_get calls to retrieve items in batches.

Frequently Asked Questions about MCP Memory Keeper

What is MCP Memory Keeper?

MCP Memory Keeper is a Model Context Protocol (MCP) server that provides persistent context management for claude ai coding assistants, allowing you to save and restore conversation context, create checkpoints, and organize information across sessions to prevent losing important work history and decisions during It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Memory Keeper?

Install via npm with the command: npx -y mcp-memory-keeper. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with MCP Memory Keeper?

MCP Memory Keeper works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Memory Keeper free to use?

Yes, MCP Memory Keeper is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

MCP Memory Keeper Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to MCP Memory Keeper? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "mcp-memory-keeper": { "command": "npx", "args": ["-y", "mcp-memory-keeper"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Memory Keeper?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides