# Engram MCP server

> Provides a shared markdown-based memory for AI assistants that syncs with Obsidian and supports semantic and keyword search.

- Repository: https://github.com/engram-app/engram
- Page: https://hostedmcp.org/servers/engram-app/engram
- Transport: remote
- Stars: 2
- Latest version: 0.85.0

## Install

### Claude Code

```sh
claude mcp add --transport http engram https://mcp.engram.page/
```

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

```json
{
  "mcpServers": {
    "engram": {
      "url": "https://mcp.engram.page/"
    }
  }
}
```

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

```json
{
  "servers": {
    "engram": {
      "type": "http",
      "url": "https://mcp.engram.page/"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"engram","type":"http","url":"https://mcp.engram.page/"}'
```

### Codex

```sh
codex mcp add engram --url https://mcp.engram.page/
```

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

```toml
[mcp_servers.engram]
url = "https://mcp.engram.page/"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http engram https://mcp.engram.page/
```

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

```json
{
  "mcpServers": {
    "engram": {
      "url": "https://mcp.engram.page/",
      "type": "http"
    }
  }
}
```

## FAQ

### Can I use different embedding models?

Yes, you can switch to Voyage AI by updating your environment variables.
