Access

Provides access to Microsoft Access and SQLite databases with import/export and note management.
  • python

5

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "scanzy-mcp-server-access-mdb": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "fastmcp",
        "--with",
        "pandas",
        "--with",
        "sqlalchemy-access",
        "--with",
        "openpyxl",
        "fastmcp",
        "run",
        "path/to/repo/server.py"
      ]
    }
  }
}

You can use the Databases MCP Server to let an MCP client interact with Microsoft Access and SQLite 3 databases. It supports importing and exporting CSV and Excel data, and lets you attach human-friendly notes to files. This server can read and modify any data in connected databases, so use it with care.

How to use

You interact with the server through an MCP client. Start by ensuring the server is running in your environment and that your client is configured to connect to it. Common tasks you can perform include listing active databases, creating new ones, connecting to existing files, executing queries to read data, and updating data. You can also import data from CSV or Excel files into a database table and export data from a table to CSV. Additionally, you can read and write notes associated with database files to keep human-friendly context.

Key actions you’ll typically perform include: list active databases, connect to a database (or create an in-memory one if you don’t specify a file), run SQL queries to retrieve or modify data, and manage imports/exports for CSV and Excel formats. You can also read notes from a file or directory and write notes that link to a database or file, helping you track data context over time.

When you configure the MCP client, you’ll point it at the server’s MCP endpoint or local process, then issue commands through the client’s interface. The server’s capabilities include table discovery, data manipulation via SQL, and file-based operations for notes and data imports/exports. Remember that large or sensitive databases may require appropriate access controls and careful operation to avoid data loss.

How to install

Prerequisites you need to prepare before installing this MCP server: a Python environment, a Node-based runtime for MCP orchestration (such as uv), and Git to obtain the codebase. Verify you have Python 3.x and Node available on your system before proceeding.

  1. Clone the project to your local machine or server. 2) Create or update the MCP configuration to include the server you want to run. 3) Start the MCP host or runtime that will load the MCP configuration and launch the server process.

Concrete configuration snippet you will add to your MCP host configuration includes the server entry for Access databases. The configuration uses the stdio approach to launch the server binary within your MCP runtime, passing the required modules and the path to the server script.

Configuration details

The server is configured to expose an MCP server named access_mdb that runs in a local process (stdio) using the following command and arguments: the runtime command uv with a sequence of flags and module inclusions, followed by the actual script path that implements the server.

Security and cautions

This server has full access to all connected databases. Exercise caution to avoid unintentional data reading or modification. Limit access to trusted clients and ensure proper authentication and authorization controls are in place where you deploy the MCP runtime.

Notes and considerations

You can manage multiple databases simultaneously. The server provides utilities to create new databases, connect to existing files, or work with in-memory databases when no file path is provided. Imported or exported data from CSV and Excel files is supported, with limitations noted for Excel handling.

Examples and tips

Use the provided configuration snippet to register the Access/MDB based MCP server in your MCP host. Then connect your client to this server to start listing databases, connecting to files, executing queries, and performing data import/export tasks.

Notes about tools and capabilities

The server exposes a set of capabilities organized into tools. You can list active databases, create new ones, connect to and disconnect from databases, run SQL queries to read or modify data, import and export CSV data, import Excel data, and manage file notes. You can read notes from a file or directory and write notes linked to a database to preserve context.

Troubleshooting

If you encounter issues starting the server, verify your MCP host configuration includes the correct stdio command and arguments, ensure the required Python and Node components are installed, and check for any missing dependencies such as data handling libraries. Review any error messages for paths to the server script and ensure the path is accessible by the host process.

Available tools

list

List all active databases available in the server.

create

Create a new database file (for Microsoft Access, copies the empty.mdb template).

connect

Connect to an existing database file, or creates an in-memory database if the file is not specified.

disconnect

Close a database connection. For in-memory databases, this will clear all its data.

query

Execute a SQL query to retrieve data from a database.

update

Execute a SQL query to insert/update/delete data in a database.

import_csv

Imports data from a CSV file into a database table.

export_csv

Exports data from a database table to a CSV file.

import_excel

Imports data from an Excel file into a database table.

read_notes

Reads notes from the specified file, or discovers notes in the specified directory.

write_notes

Writes notes to the specified file, or linked to the specified database.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational