# Verbative Memory MCP server

> Provides an on-device, dual-layer memory system that captures and recalls distilled facts and event ledgers for AI coding agents.

- Repository: https://github.com/verbative/verbative-memory
- Page: https://hostedmcp.org/servers/verbative/verbative-memory
- Transport: stdio
- Stars: 1
- Latest version: 1.1.3

## Install

### Claude Code

```sh
claude mcp add verbative-memory -- npx -y verbative-memory
```

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

```json
{
  "mcpServers": {
    "verbative-memory": {
      "command": "npx",
      "args": [
        "-y",
        "verbative-memory"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "verbative-memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "verbative-memory"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"verbative-memory","type":"stdio","command":"npx","args":["-y","verbative-memory"]}'
```

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

```json
{
  "mcpServers": {
    "verbative-memory": {
      "command": "npx",
      "args": [
        "-y",
        "verbative-memory"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add verbative-memory -- npx -y verbative-memory
```

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

```toml
[mcp_servers.verbative-memory]
command = "npx"
args = ["-y", "verbative-memory"]
```

### Gemini CLI

```sh
gemini mcp add -s user verbative-memory npx -- -y verbative-memory
```

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

```json
{
  "mcpServers": {
    "verbative-memory": {
      "command": "npx",
      "args": [
        "-y",
        "verbative-memory"
      ]
    }
  }
}
```

## FAQ

### Where is the memory data stored?

Memories are stored locally as plain, human-readable files within your project repository.

### Does using this server require an internet connection?

After the initial download of the engine and models, the recall process runs fully offline.

### What operating systems are supported?

The system currently supports macOS (Apple silicon) and Windows 10/11 (x64), with Linux planned for the future.

### Is my code uploaded to the cloud?

No, all processes including capture, embeddings, and reranking run locally on your machine.