Engram MCP Server

Engram gives any AI model human-like memory that persists across sessions, systems, and restarts. Connect it once and every AI you use — Claude Code, Ollama, or any custom integration — shares a…

Local serverstdio

What is the Engram MCP Server?

Engram is an MCP project maintained in the ayvazyan10/engram repository. The maintainer describes its purpose as “Engram gives any AI model human-like memory that persists across sessions, systems, and restarts. Connect it once and every AI you use — Claude Code…”. Read the project documentation for the complete scope.

Installation

The documented npm package is @engram-ai-memory/mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.

Configuration values

The example declares ENGRAM_DB_PATH. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

How to install the Engram MCP Server

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@engram-ai-memory/mcp@latest"
      ],
      "env": {
        "ENGRAM_DB_PATH": "~/.engram/engram.db"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

VariableDescriptionRequired
ENGRAM_DB_PATHDeclared in the maintainer’s client configuration.Check documentation