MCP Memory Server
BasicMCP Memory Server is a server designed to implement long-term memory capabilities for AI assistants, utilizing PostgreSQL and pgvector for efficient vector similarity search. It provides automated embedding generation and a RESTful API for memory operations.
000
Overview
MCP Memory Server is a server designed to implement long-term memory capabilities for AI assistants, utilizing PostgreSQL and pgvector for efficient vector similarity search. It provides automated embedding generation and a RESTful API for memory operations.
Installation
1Install the package
npx
Set up PostgreSQL with the pgvector extension, install the necessary dependencies, configure environment variables, and start the server.2Add to Claude
Add this configuration to your claude_desktop_config.json:
claude_desktop_config.json
{
"mcpServers": {
"mcp-memory-server": {
"command": "npx",
"args": [
"-y",
"Set up PostgreSQL with the pgvector extension, install the necessary dependencies, configure environment variables, and start the server."
]
}
}
}3Verify installation
Restart Claude Desktop, then ask:
"What tools do you have available from MCP Memory Server?"
Prerequisites
- Node.js 18 or higher
- npm or npx available
- Claude Desktop or Claude API access
Configuration
No configuration required. This server works out of the box.
Usage Examples
List Resources
"What resources are available in MCP Memory Server?"
Claude will query available resources and return a list of what you can access.
Get Details
"Show me details about [specific item] in MCP Memory Server"
Claude will fetch and display detailed information about the requested item.
Create New
"Create a new [item] in MCP Memory Server with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
Works with MCP Memory Server
See what tools in your stack can connect to AI.
Run free scan
Need help with MCP integration?
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.