MCP Server Altibase

🚀 Altibase MCP Server

An implementation of the Model Context Protocol (MCP) server that provides database interaction and business intelligence capabilities through Altibase.

This server allows you to run SQL queries, analyze business data, and automatically generate business insights memos. The source code is hosted at https://github.com/hesslee/mcp-server-altibase, based on https://github.com/modelcontextprotocol/servers/tree/main/src/sqlite. This package is uploaded to https://pypi.org/project/mcp-server-altibase.

✨ Features

Resources

The server exposes a dynamic resource:

• memo://insights: A continuously updated business insights memo that aggregates all insights discovered during the analysis process.
  • It is automatically updated when new insights are added using the postscript tool.

Prompts

The server provides a demo prompt:

• mcp-demo: An interactive prompt that guides users through database operations.
  • Required parameter: topic (string) - The business area to analyze.
  • Automatically generates appropriate database schemas and sample data.
  • Guides users through analysis and insights generation.
  • Integrates into the business insights memo.

Tools

The server provides six core tools:

Query Tools

• read_query
  • Executes a SELECT query to read data from the database.
  • Input:
    • query (string): The SELECT SQL query to execute.
  • Returns: The query results as an array of objects.
• write_query
  • Executes an INSERT, UPDATE, or DELETE query.
  • Input:
    • query (string): The SQL modification query.
  • Returns: { affected_rows: number }
• create_table
  • Creates a new table in the database.
  • Input:
    • query (string): The CREATE TABLE SQL statement.
  • Returns: Confirmation that the table has been created.

Schema Tools

• list_tables
  • Gets a list of all tables in the database.
  • No input required.
  • Returns: An array of table names.
• describe_table
  • Views the schema information of a specific table.
  • Input:
    • table_name (string): The name of the table to describe.
  • Returns: Detailed information about the table's columns and their data types.

Mutation Tools

• execute_trigger
  • Executes a trigger in the database.
  • Input:
    • trigger_name (string): The name of the trigger to execute.
  • Returns: The status of the operation result.

📦 Installation

Prerequisites

To use this MCP server, you need the following prerequisites:

1. Python 3.6 or higher
2. Altibase database installation: Refer to the Altibase documentation for installation and configuration.
3. ODBC driver: Ensure that an ODBC driver compatible with Altibase is installed on your system.

Unixodbc Setup Example (Linux)

Install unixodbc

On Debian-based systems:

sudo apt-get install unixodbc-dev

On Red Hat-based systems:

sudo yum install unixODBC-devel

Configure odbc.ini

Create or edit the /etc/odbc.ini file and add the following content:

[Altibase_DSN]
Description = Altibase ODBC Driver
Driver      = /usr/lib/x86_64-linux-gnu/odbc/altibase.so
Database    = your_database_name
User        = your_username
Password    = your_password

Odbc Configuration Example (Windows)

Install ODBC Driver

1. Download and install the Altibase ODBC driver.
2. Add the driver to the system path.

Create DSN

1. Open "Control Panel" > "System and Security" > "Administrative Tools" > "Data Sources (ODBC)".
2. Click the "Add" button and select the Altibase ODBC driver.
3. Fill in the DSN name and other necessary information.

💻 Usage Examples

Usage with Claude Desktop

Using uv

1. Install and run Claude Desktop.
2. Enter the following command in the terminal:

uv --directory /path/to/repo clone hess/mcp-server-altibase

3. Then run:

uv --directory /path/to/repo run mcp-server-altibase --odbc-dsn "your_dsn_name"

Using uvx

1. Enter the following command in the terminal:

uvx hess/mcp-server-altibase run -- odbc-dsn="your_dsn_name"