ukkit/memcord
If you are the rightful owner of memcord and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
MemCord MCP Server is a Model Context Protocol server designed to manage chat memory with features like automatic summarization, intelligent search, and file sharing.
MEMCORD v2.3.5 (mcp server)This privacy-first, self-hosted MCP server helps you organize chat history, summarize messages, search across past chats with AI — and keeps everything secure and fully under your control. |
Never Lose Context Again
Transform your Claude conversations into a searchable, organized knowledge base that grows with you
✨ Core Benefits
- 🧠 Infinite Memory - Claude remembers everything across unlimited conversations with intelligent auto-summarization
- 🔒 Your Data, Your Control - 100% local storage with zero cloud dependencies or privacy concerns
- 🎯 Effortless Organization - Smart tags and folders that organize themselves around your workflow
- 🔗 Intelligent Merging - Automatically combines related conversations while eliminating duplicates
What's new in v2.3.5
Enhanced VSCode and GitHub Copilot Integration:
- Added comprehensive VSCode configuration templates (.vscode/mcp.json.example)
- Implemented 16 reusable prompt templates for GitHub Copilot workflows
- Created automated verification script for VSCode setup validation
- Added MCP registry metadata (package.json) for marketplace discovery
- Full integration test suite for VSCode/Copilot compatibility
- Complete documentation for enterprise deployment, security, and workflows
🚀 Quick Start
curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash
This will:
- Download and setup memcord
- Set Up Python Virtual Environment using uv
- Update claude_desktop_config.json & README.md with Installation Path
Manually update existing setup
uv pip install -e .
uv lock
Claude Desktop
{
"mcpServers": {
"memcord": {
"command": "uv",
"args": [
"--directory",
"</path/to/memcord>",
"run",
"memcord"
],
"env": {
"PYTHONPATH": "</path/to/memcord>/src"
}
}
}
}
VSCode with GitHub Copilot
Prerequisites:
- VSCode 1.102+ (MCP support is GA)
- GitHub Copilot subscription
- Organization/Enterprise MCP policy enabled (if applicable)
Option 1: Workspace Configuration (Recommended)
Copy the example configuration to your workspace:
mkdir -p .vscode
cp .vscode/mcp.json.example .vscode/mcp.json
Or create .vscode/mcp.json manually:
{
"servers": {
"memcord": {
"command": "uv",
"args": [
"--directory",
"${workspaceFolder}",
"run",
"memcord"
],
"env": {
"PYTHONPATH": "${workspaceFolder}/src"
}
}
}
}
Option 2: Global User Configuration
- Open Command Palette (Ctrl+Shift+P / Cmd+Shift+P)
- Run:
MCP: Open User Configuration - Add memcord server configuration to
mcp.json
Option 3: Source-Controlled Configuration
Copy root-level configuration (recommended for teams):
cp .mcp.json.example .mcp.json
GitHub Copilot Agent Mode: Once configured, memcord tools are available in Copilot agent mode. Use natural language:
- "Create a memory slot for this project"
- "Search my memories for API design decisions"
- "Query past conversations about authentication"
- Detailed instructions for VSCode and GitHub Copilot integration.
Claude Code MCP (🧪 BETA)
Add MCP server for your project - check README.md for installation path
claude mcp add-json memcord '{"type":"stdio","command":"uv","args":["--directory","</path/to/memcord>","run","memcord"],"env":{"PYTHONPATH":"</path/to/memcord>/src"}}'
Verify installation
claude mcp list
claude mcp get memcord
Add at top of your CLAUDE.md file
memcord_name "NAME_OF_YOUR_PROJECT"
Manual Installaion
# Traditional installation method
git clone https://github.com/ukkit/memcord.git
cd memcord
uv venv
source .venv/bin/activate
uv pip install -e .
# Replace </path/to/memcord/> in claude_desktop_config.json to the path where you installed it manually
- Detailed setup for Claude Code, Claude Desktop, and other MCP applications.
💻 Basic Usage
# Create a memory slot and save conversation
memcord_name "project_meeting"
memcord_save "Our discussion about the new API design..."
memcord_save_progress
# Use existing memory slot
memcord_use "project_meeting" 🆕
# Navigate timeline - select specific entries
memcord_select_entry "2 hours ago" # or "latest", index, timestamp 🆕
# Privacy control - activate zero mode (no saving)
memcord_zero # No memory will be saved until switched to another slot
# Search and query your memories
memcord_search "API design decisions"
memcord_query "What did we decide about authentication?"
# Merge related conversations
memcord_merge ["project_meeting", "api_notes"] "consolidated_project" 🆕
Refer to 📖 for Advanced Mode and detailed documentation for all 19 tools with examples and parameters.
📚 Documentation
⚠️ Documentation updates in progress
- 📚 - Complete setup instructions for all MCP applications
- 📃 - Complete list of features
- 📖 - Detailed documentation for all 19 tools
- 📥 - Comprehensive guide for Phase 3 features 🆕
- 🔍 - Advanced search features and natural language queries
- 🗂️ - Real-world workflows and practical use cases
- ⚙️ - Technical details and file formats
- 🛠️ - Common issues and solutions
💎 If you find this project helpful, consider:
- 🌟 Starring the repository on GitHub
- 🤝 Support Development
- 🐛 Reporting bugs and suggesting features
MIT License - see LICENSE file for details.