Memcord

v1.0.0Knowledge & Memorystable

🐍 🏠 🐧 🍎 - A MCP server that keeps your chat history organized and searchable—with AI-powered summaries, secure memory, and full control.

ai-assistantai-memoryantigravitychat-historyclaude-desktop
Share:
66
Stars
0
Downloads
0
Weekly
0/5

What is Memcord?

Memcord is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 🏠 🐧 🍎 - a mcp server that keeps your chat history organized and searchable—with ai-powered summaries, secure memory, and full control.

🐍 🏠 🐧 🍎 - A MCP server that keeps your chat history organized and searchable—with AI-powered summaries, secure memory, and full control.

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

Features

  • 🐍 🏠 🐧 🍎 - A MCP server that keeps your chat history organize

Use Cases

Organize and search chat history with summaries.
Store AI-powered secure memory of conversations.
Maintain searchable conversation archives.
ukkit

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx memcord

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 Memcord

Memcord is a local, privacy-first MCP server that gives AI assistants persistent, searchable memory across conversations by saving, organizing, and retrieving chat history on your own machine. It exposes 23 tools covering everything from saving conversation snapshots with AI-generated summaries to full-text and semantic search across past sessions, with zero cloud dependencies. Developers and power users who want their AI assistant to remember context, decisions, and prior work across separate sessions will find it especially valuable.

Prerequisites

  • Python 3.9 or later installed on your system
  • uv package manager installed (run 'pip install uv' or see https://github.com/astral-sh/uv)
  • An MCP-compatible client such as Claude Desktop
  • Git to clone the repository (or use the one-line installer script)
1

Install Memcord using the automated installer

The fastest way to get started is the platform installer, which sets up the Python environment and generates the Claude config automatically.

# macOS / Linux
curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash

# Windows PowerShell
irm https://github.com/ukkit/memcord/raw/main/install.ps1 | iex
2

Or install manually with uv

Clone the repository, create a virtual environment with uv, install dependencies, and run the config generator to produce the Claude Desktop config snippet.

git clone https://github.com/ukkit/memcord.git
cd memcord
uv venv
uv pip install -e .
uv run python scripts/generate-config.py
3

Add the generated config to Claude Desktop

The generate-config.py script prints a JSON snippet. Merge it into your claude_desktop_config.json at ~/Library/Application Support/Claude/ (macOS). Restart Claude Desktop after saving.

{
  "mcpServers": {
    "memcord": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/memcord", "python", "-m", "memcord"]
    }
  }
}
4

Initialize a project memory slot

In your Claude conversation, bind the current working directory to a named memory slot so Memcord knows which project context to use.

5

Configure your preferred summarization backend

Memcord supports four summarization backends. The default (nltk) requires no extra installs. For AI-powered abstractive summaries, install the transformers extra.

# Install semantic or transformer backends (optional)
pip install "memcord[semantic]"
pip install "memcord[transformers]"

# Set via the MCP tool (tell Claude):
# memcord_configure action="set" key="summarizer_backend" value="transformers"

Memcord Examples

Client configuration

Claude Desktop config entry for Memcord, running the server via uv from the cloned repository directory.

{
  "mcpServers": {
    "memcord": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/Users/yourname/memcord",
        "python",
        "-m",
        "memcord"
      ]
    }
  }
}

Prompts to try

Example instructions to give Claude once Memcord is connected and a session is active.

- "Save this conversation to my project-alpha memory slot with a summary"
- "Search my memory for anything about the API design decisions we made"
- "What did we decide about authentication in previous sessions?"
- "Show me a summary of my last five saved conversations"
- "Enable privacy mode so nothing is saved for this session"

Troubleshooting Memcord

memcord tools do not appear in Claude after adding the config

Confirm the directory path in the config points to where you cloned the repo, and that uv is on the PATH Claude Desktop uses (full path may be needed, e.g. /Users/yourname/.cargo/bin/uv). Restart Claude Desktop completely after config changes.

Summarization is very slow or times out

The 'transformers' backend downloads a BART model on first use, which can take several minutes. Switch to the faster 'nltk' or 'sumy' backend: tell Claude 'memcord_configure action=set key=summarizer_backend value=nltk'.

memcord_search returns no results for conversations I know were saved

Check that memcord_init was run in the project directory to bind the correct slot. Search uses the slot associated with the current working directory; if you are in a different directory the data may be in a different slot.

Frequently Asked Questions about Memcord

What is Memcord?

Memcord is a Model Context Protocol (MCP) server that 🐍 🏠 🐧 🍎 - a mcp server that keeps your chat history organized and searchable—with ai-powered summaries, secure memory, and full control. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Memcord?

Follow the installation instructions on the Memcord GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Memcord?

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

Is Memcord free to use?

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

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.

Quick Config Preview

{ "mcpServers": { "memcord": { "command": "npx", "args": ["-y", "memcord"] } } }

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

Read the full setup guide →

Ready to use Memcord?

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