This MCP server provides an interface for AI to interact with Microsoft Access and SQLite 3 databases. It supports managing databases, executing SQL queries, importing and exporting data to CSV and Excel (with some limitations for Excel), and recording notes about files. The server runs within uv (Python) and leverages FastMCP alongside libraries like pandas and SQLAlchemy-access to bridge the AI with Access and SQLite data sources. Tools available include: creating and connecting to databases, listing databases and tables, running SQL queries to read or modify data, and importing/exporting data to CSV (and Excel where supported). Remember that this server has full access to connected databases, so use it with appropriate safeguards and permissions.

Prerequisites:

• Python 3.8+ installed on your system
• Access to install Python packages (pip)

Installation steps:

1. Clone the repository: git clone https://github.com/your-org/scanzy-mcp-server-access-mdb.git cd scanzy-mcp-server-access-mdb

2. Create and activate a virtual environment (recommended): python -m venv venv

   Windows

   venv\Scripts\activate

   macOS/Linux

   source venv/bin/activate

3. Install dependencies (via uv and required Python packages): pip install fastmcp pandas sqlalchemy-access openpyxl

4. Run the server using uv as described in the README configuration: uv run --with fastmcp --with pandas --with sqlalchemy-access --with openpyxl fastmcp run path/to/repo/server.py

5. Point your MCP host to the server endpoint and use the provided tools to manage databases and data.

Notes and tips:

• The Excel export path is not fully implemented; consider using the recommended Excel workaround via haris-musa/excel-mcp-server for Excel exports.
• The server supports multiple databases simultaneously; you can connect to several databases and manage them concurrently.
• When using Access (.mdb/.accdb) files, ensure file paths are accessible by the server process and proper permissions are set.
• If you encounter issues with UVX, the readme mentions creating a package and publishing to PyPI; ensure you’re using a compatible uv runner for your environment.
• For long-running tasks, monitor memory usage since importing large CSV/Excel files with pandas can be resource-intensive.