endlessblink/Like-I-Said-memory-mcp-server
3.5
If you are the rightful owner of Like-I-Said-memory-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Like-I-Said MCP v2 is a memory server designed to provide AI assistants with persistent memory capabilities, allowing them to remember conversations and context across sessions.
Tools
6
Resources
0
Prompts
0
Like I Said - MCP Memory Server
A Model Context Protocol (MCP) server for persistent AI assistant memory with web dashboard interface.
✨ Features
- 🧠 Persistent Memory: Store and retrieve memories across conversations
- 🌐 Web Dashboard: Modern React interface to view and manage memories
- 🔄 Real-time Updates: Live dashboard with search and filtering
- ⚡ Easy Setup: Multiple deployment options
- 🔧 MCP Compatible: Works with Claude Desktop, Cursor, and other MCP clients
🚀 Quick Start
1. Install Dependencies
npm install
2. Development Mode (Frontend + Backend)
npm run dev:full
- Frontend: http://localhost:5173 (React dashboard)
- Backend: http://localhost:3001 (API server)
3. Production Mode (MCP Server Only)
npm start
🔧 MCP Configuration
Claude Desktop Setup
- Copy
claude-desktop-config.template.json
to your Claude config directory - Update the path to point to your project location
- Rename to
claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"like-i-said-memory": {
"command": "node",
"args": ["PATH_TO_YOUR_PROJECT/server.js"]
}
}
}
🛠️ Available Tools
add_memory(key, value, context?)
: Store a memory with optional contextget_memory(key)
: Retrieve a memory by keylist_memories(prefix?)
: List all memory keys (with optional prefix filter)delete_memory(key)
: Delete a memory by key
📱 Web Dashboard
The dashboard provides:
- Memory Browser: View all stored memories in a searchable table
- Search & Filter: Find memories by key, value, or tags
- Add/Edit: Create and modify memories through the UI
- Real-time: Automatically syncs with the MCP server data
🗂️ Data Storage
Memories are stored in memory.json
with structure:
{
"memory_key": {
"value": "The actual memory content",
"context": {
"type": "category",
"tags": ["tag1", "tag2"]
},
"timestamp": "2025-01-01T00:00:00.000Z"
}
}
📜 Scripts
npm start
- Start MCP server onlynpm run dashboard
- Start web dashboard onlynpm run dev:full
- Start both servers for developmentnpm run build
- Build frontend for productionnpm run pm2:start
- Start with PM2 process manager
🔧 PM2 Deployment (Optional)
- Copy and customize
ecosystem.config.template.json
- Install PM2:
npm install -g pm2
- Start:
npm run pm2:start
📋 Development
Built with:
- Backend: Node.js, Express
- Frontend: React, TypeScript, Vite, Tailwind CSS
- UI: Shadcn/ui components
📄 License
MIT License - see LICENSE file for details.