# Logos MCP server

> Provides a local-first memory and continuity layer that allows different AI coding agents to share context and resume work from where another left off.

- Repository: https://github.com/Coder8124/logos
- Page: https://hostedmcp.org/servers/coder8124/logos
- Transport: stdio
- Stars: 4
- License: Apache-2.0

## Install

### Claude Code

```sh
claude mcp add logos -- npx -y @noeton/logos
```

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

```json
{
  "mcpServers": {
    "logos": {
      "command": "npx",
      "args": [
        "-y",
        "@noeton/logos"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "logos": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@noeton/logos"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"logos","type":"stdio","command":"npx","args":["-y","@noeton/logos"]}'
```

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

```json
{
  "mcpServers": {
    "logos": {
      "command": "npx",
      "args": [
        "-y",
        "@noeton/logos"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add logos -- npx -y @noeton/logos
```

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

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

### Gemini CLI

```sh
gemini mcp add -s user logos npx -- -y @noeton/logos
```

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

```json
{
  "mcpServers": {
    "logos": {
      "command": "npx",
      "args": [
        "-y",
        "@noeton/logos"
      ]
    }
  }
}
```

## FAQ

### How does Logos handle data privacy?

Logos is local-first; the vault is a folder of markdown files on your machine and nothing is uploaded.

### Can I use Logos with different AI agents?

Yes, it works with Claude Code, Codex, Cursor, Claude Desktop, Cline, Devin, GitHub Copilot, and any other tool that supports MCP.

### What happens if I delete the index file?

You will lose nothing; you can simply run the index command to rebuild it.

### Does it require an LLM to function?

No model is required for basic functionality; search falls back to full-text search if local embeddings are unavailable.