# Engram MCP server

> Transforms LLM conversation history into structured semantic knowledge using episodic memory capture and graph-based consolidation.

- Repository: https://github.com/devinmlowe/engram
- Page: https://hostedmcp.org/servers/devinmlowe/engram
- Transport: stdio
- Stars: 1
- License: MIT
- Latest version: 0.5.0

## Install

### Claude Code

```sh
claude mcp add --env 'ENGRAM_MCP_TOKEN=<YOUR_ENGRAM_MCP_TOKEN>' engram -- npx -y @devinmlowe/engram
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@devinmlowe/engram"
      ],
      "env": {
        "ENGRAM_MCP_TOKEN": "<YOUR_ENGRAM_MCP_TOKEN>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "engram": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@devinmlowe/engram"
      ],
      "env": {
        "ENGRAM_MCP_TOKEN": "<YOUR_ENGRAM_MCP_TOKEN>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"engram","type":"stdio","command":"npx","args":["-y","@devinmlowe/engram"],"env":{"ENGRAM_MCP_TOKEN":"<YOUR_ENGRAM_MCP_TOKEN>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@devinmlowe/engram"
      ],
      "env": {
        "ENGRAM_MCP_TOKEN": "<YOUR_ENGRAM_MCP_TOKEN>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add engram --env 'ENGRAM_MCP_TOKEN=<YOUR_ENGRAM_MCP_TOKEN>' -- npx -y @devinmlowe/engram
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.engram]
command = "npx"
args = ["-y", "@devinmlowe/engram"]

[mcp_servers.engram.env]
ENGRAM_MCP_TOKEN = "<YOUR_ENGRAM_MCP_TOKEN>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'ENGRAM_MCP_TOKEN=<YOUR_ENGRAM_MCP_TOKEN>' engram npx -- -y @devinmlowe/engram
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@devinmlowe/engram"
      ],
      "env": {
        "ENGRAM_MCP_TOKEN": "<YOUR_ENGRAM_MCP_TOKEN>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `ENGRAM_MCP_TOKEN` | no | yes | Bearer token forwarded to the HTTP daemon when it requires one |
| `ENGRAM_DB_PATH` | no | no | SQLite database path (default: <data dir>/engram.db, i.e. ~/.local/share/engram/engram.db) |
| `ENGRAM_MCP_PORT` | no | no | Port of the optional engram HTTP daemon to bridge to (default 9907) |
| `ENGRAM_MCP_STANDALONE` | no | no | Set to 1 to never bridge: always run the full server in-process |

## FAQ

### What is Engram?

Engram is a local-first cognitive memory system that transforms raw LLM conversation history into structured, consolidated knowledge using episodic and semantic memory architectures.

### How do I install Engram for Claude Code?

You can install it as a plugin directly in Claude Code using the commands /plugin marketplace add devinmlowe/engram and /plugin install engram@engram.

### Does Engram require an LLM provider?

Search, remember, and the web visualizer work without an LLM, but at least one provider is needed for extraction and dream consolidation.
