> ## Documentation Index
> Fetch the complete documentation index at: https://docs.myquery.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MotherDuck

> cloud and local versions of DuckDB.

## **Security & Architecture Overview**

Before connecting your data, it is critical to understand how MyQuery interacts with your infrastructure:

* **Schema-Only Access:** MyQuery does **not** ingest or store your raw database records. We only read the metadata (table names, column types, and foreign key relationships) to build a semantic map for the AI.
* **Encrypted Storage:** All connection credentials and "maps" are encrypted at rest using industry-standard AES-256 encryption.
* **Whitelisting:** To allow MyQuery to reach your database, you must whitelist our outbound IP addresses in your firewall or cloud security groups (e.g., AWS Security Groups, Azure Firewall).

## **MotherDuck (DuckDB Cloud)**

The serverless cloud version of DuckDB.

### **Connection Method: Token**

* **Connection String (Required):** e.g.,

  ```
  md:my_database
  ```

  .
* **Token (Required):** Your MotherDuck API token.
* **Schema (Optional):** Specify the schema if not using

  ```
  main
  ```

  .

## **DuckDB (Local File)**

High-performance analytical database for local files.

### **Connection Method A: Database File**

* **Upload File:** Securely upload your

  ```
  .duckdb
  ```

  file.

### **Connection Method B: Multi-File (CSV/Parquet)**

* **Multiple Files:** Upload a batch of

  ```
  .csv
  ```

  or

  ```
  .parquet
  ```

  files. MyQuery will create a virtual DuckDB instance, treating each filename as a table.