Microsoft Access Database
About
Allows AI to interact with Microsoft Access databases, supporting data import and export via CSV files.
Details
- Author
- scanzy
- Categories
- Database, Other
Jump to
Setup
Install Microsoft Access Database in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/scanzy/mcp-server-access-mdb
Follow the installation instructions in the repository README, then restart your MCP client.
Allows AI to interact with Microsoft Access databases, supporting data import and export via CSV files.
Databases MCP Server (Access and SQLite 3)
A simple MCP server to let AI interact with Microsoft Access and SQLite 3 databases. Supports import/export with CSV and Excel files, and store human-readable notes about files.
WARNING: This server has full access to databases, so it can read and modify any data in it.Use with cautionto avoid data loss!
To use this MCP server with Claude Desktop (or any other MCP host), clone the repo and add the following to yourconfig.json:
{ "mcpServers": { "access-mdb": { "command": "uv", "args": [ "run", "--with", "fastmcp", "--with", "pandas", "--with", "sqlalchemy-access", "--with", "openpyxl", "fastmcp", "run", "path/to/repo/server.py" ], } } }
Dev note: to use with uvx, we need to create a package and publish it to PyPI.
- 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.
Note: useconnecttool withreadOnly=trueto open a database in read-only mode. For SQLite in-memory databases, read-only mode is not supported.
- 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.
Note: Excel export is not implemented, use haris-musa/excel-mcp-server instead. The main problem is tracking the index of the rows and columns in the Excel file, to correctly import/export data to the same cells, and/or insert new rows/columns. In addition, merged cells complicate the process, it would be too complex to implement.
By default, database driver detection is based on file extension:
- Microsoft Access:.mdband.accdb
- SQLite 3:.db,.sqlite, and.sqlite3
If database path is not specified (empty string), an in-memory SQLite database will be created.
To let the server open or create a database file without relying on the extension (for example, if your database file has a non-standard extension), you can specify the driver explicitly using thedriverparameter in theconnectorcreatetool.
- driver="access"forMicrosoft Access
- driver="sqlite"forSQLite 3
- driver="auto"(default) automatically detects the driver based on the file extension
- test_tools.py: Functions to test individual MCP tools.
- test_mcp.py: Tests all MCP tools in a typical workflow.
- README.md: This file, with general information about the project.
- LICENSE: MIT license.
Scouting scripts, used in the first stages to develop basic functionality:
- scouting_mdb.py: SQLAlchemy and pandas to interact with Microsoft Access databases.
- scouting_csv.py: SQLAlchemy and pandas to interact with CSV files.
- Add tool to create a new database, copying empty.mdb to the specified path.
- Add the ability to connect to multiple databases at the same time.
- Add tool to list all tables in the database.
- Add tools to import/export data from/to CSV files.
- Add tools to import data from/to Excel files.
- Add prompt to guide AI asking info to the user about the database.
- Store info about files (.AInotes files), to retrieve it later.
- Add driver parameter to manage databases without relying on file extension.
- Add tool to remember imported/exported CSV and Excel files.
Generate realistic multi-table test data with foreign keys that resolve and aggregates that reconcile, returned with an integrity check. Seeds Postgres, MySQL and SQLite from your own schema, or exports CSV/JSON/SQL/Parquet. Deterministic, so the same schema and seed give the same rows.
Official MCP server for dbt (data build tool) providing integration with dbt Core/Cloud CLI, project metadata discovery, model information, and semantic layer querying capabilities.
Provides AI assistants with a secure and structured way to explore and analyze data in GreptimeDB.
Build robust data workflows, integrations, and analytics on a single intuitive platform.
Query and analyze data with MotherDuck and local DuckDB
An MCP server that provides tools to interact with Powerdrill datasets, enabling smart AI data analysis and insights.
Slingshot MCP introduces Slingshot Aerospace’s space data platform in your AI chat—explore satellites, orbits, and Portal insights through Slingshot’s hosted server.
A collection of tools for managing the platform, addressing data quality and reading and writing to Teradata Database.
Interact with Verodat AI Ready Data platform
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
