Skip to main content
Glama
Sign In
Claude Memory MCP

Claude Memory MCP

by adeeljames
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

🧠 Claude Memory MCP

A lightweight Model Context Protocol (MCP) server that gives Claude Desktop persistent memory across conversations. It stores, summarizes, and retrieves conversation history so Claude always remembers your context.

✨ Features

Feature

Description

Persistent Memory

Saves every conversation turn to a local memory.json file

Auto-Summarization

Automatically compresses history after 10 turns to keep context lean

Fast Context Loading

Returns summary + last 3 turns on demand — no bloat

One-command Setup

Powered by uv — no virtualenv juggling needed

Zero Latency

Runs locally over stdio — no network calls

Related MCP server: mcp-assist-memory

🛠️ Tools Exposed

Tool

Description

get_context

Load compressed memory (summary + last 3 turns). Call at the start of every conversation.

save_turn

Save one conversation turn. Call after every AI response.

clear_memory

Wipe all stored memory and start fresh.

🚀 Quick Start

Prerequisites

  • Python 3.13+

  • uv installed

1. Clone & Install

git clone https://github.com/adeeljames/claude-memory-mcp.git
cd claude-memory-mcp
uv sync

2. Run the MCP Server (for testing)

uv run python server.py

3. Add to Claude Desktop

Open your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the following under mcpServers:

{
  "mcpServers": {
    "memory-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/absolute/path/to/claude-mcp-optimize",
        "python",
        "server.py"
      ]
    }
  }
}

Replace /absolute/path/to/claude-mcp-optimize with the actual path on your machine.

Restart Claude Desktop — the memory-mcp server will appear in your tools list.

📁 Project Structure

claude-memory-mcp/
├── server.py           # MCP server — all tools defined here
├── memory.json         # Runtime memory file (auto-created, gitignored)
├── pyproject.toml      # uv project config & dependencies
├── uv.lock             # Locked dependency graph
└── README.md           # You are here

⚙️ How It Works

Claude Desktop ──stdio──► server.py ──► memory.json
                                          │
                         ┌────────────────┘
                         │
                    get_context()     → returns summary + last 3 turns
                    save_turn()       → appends to history, triggers summary at 10 turns
                    clear_memory()    → resets everything

🔧 Dependencies

Package

Purpose

mcp>=1.26.0

Model Context Protocol SDK

All dependencies are managed by uv and pinned in uv.lock.

📄 License

MIT — free to use, modify, and share.

Made with love by @muhammadadeelai

Available Tools

3 tools
clear_memoryA

Wipe all stored memory and start fresh.

Inputs: no named parameters.

get_contextA

Load compressed memory. Returns summary + last 3 turns only. Call this at the START of every conversation.

Inputs: no named parameters.

save_turnA

Save one conversation turn to memory. Call this AFTER every response.

Inputs: user_msg (required), ai_response (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a distinct, non-overlapping purpose: clearing all memory, retrieving context, and saving a turn. No ambiguity.

    Naming Consistency5/5

    All tool names follow a clear verb_noun pattern with underscores: clear_memory, get_context, save_turn. Fully consistent.

    Tool Count4/5

    With 3 tools, the set is minimal but appropriate for a focused memory management server, covering essential operations. Slightly thin but not problematic.

    Completeness3/5

    Covers basic lifecycle: create (save_turn), read (get_context), delete all (clear_memory). Missing update or selective delete functionality, which may be needed for finer control.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MCP Memory Server

      PlumyCat
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives Claude persistent memory by storing conversation context, entities, and enabling semantic search across sessions.
      34 npm
      1
      MIT

    • mcp-assist-memory

      aliomraniH
      F
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that provides a shared memory layer for Claude across claude.ai, Claude Code CLI, and Desktop, storing revisioned memory entries, session timelines, handoffs, and uploaded artifacts in SQLite.
      -

    • memory-mcp

      chenxiaofie
      A
      license
      B
      quality
      C
      maintenance
      A persistent memory MCP server for Claude Code that automatically saves conversations and retrieves relevant history across sessions to provide context.
      17
      67 PyPI
      10
      MIT

    • recall

      Zavelinski
      A
      license
      A
      quality
      D
      maintenance
      A zero-dependency MCP server for cross-session memory recall in Claude Code. Provides lexical search, listing, and retrieval of past session memories to avoid re-explaining context.
      3
      10 npm
      MIT