Altibase MCP Server
Overview
- A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through Altibase.
- This server enables running SQL queries, analyzing business data, and automatically generating business insight memos.
- This source code is maintained on https://github.com/hesslee/mcp-server-altibase
- This source code is based on https://github.com/modelcontextprotocol/servers/tree/main/src/sqlite
- This package is uploaded on https://pypi.org/project/mcp-server-altibase
Components
Resources
The server exposes a single dynamic resource:
memo://insights: A continuously updated business insights memo that aggregates discovered insights during analysis- Auto-updates as new insights are discovered via the append-insight tool
Prompts
The server provides a demonstration prompt:
mcp-demo: Interactive prompt that guides users through database operations- Required argument:
topic- The business domain to analyze - Generates appropriate database schemas and sample data
- Guides users through analysis and insight generation
- Integrates with the business insights memo
- Required argument:
Tools
The server offers six core tools:
Query Tools
-
read_query- Execute SELECT queries to read data from the database
- Input:
query(string): The SELECT SQL query to execute
- Returns: Query results as array of objects
-
write_query- Execute INSERT, UPDATE, or DELETE queries
- Input:
query(string): The SQL modification query
- Returns:
{ affected_rows: number }
-
create_table- Create new tables in the database
- Input:
query(string): CREATE TABLE SQL statement
- Returns: Confirmation of table creation
Schema Tools
-
list_tables- Get a list of all tables in the database
- No input required
- Returns: Array of table names
-
describe_table- View schema information for a specific table
- Input:
table_name(string): Name of table to describe
- Returns: Array of column definitions with names and types
Analysis Tools
append_insight- Add new business insights to the memo resource
- Input:
insight(string): Business insight discovered from data analysis
- Returns: Confirmation of insight addition
- Triggers update of memo://insights resource
Prereqisite
- Download and install Altibase server and client from http://support.altibase.com/en/product
- Unixodbc setting for Linux
- ODBC DSN setting for Windows
Unixodbc setting example for Linux
- install : sudo apt-get install unixodbc-dev
- example configuration :
$ cat /etc/odbc.ini
[PYODBC]
Driver = /home/hess/work/altidev4/altibase_home/lib/libaltibase_odbc-64bit-ul64.so
Database = mydb
ServerType = Altibase
Server = 127.0.0.1
Port = 21121
UserName = SYS
Password = MANAGER
FetchBuffersize = 64
ReadOnly = no
$ cat /etc/odbcinst.ini
[ODBC]
Trace=Yes
TraceFile=/tmp/odbc_trace.log
ODBC DSN setting example for Windows
- Altibase Windows ODBC driver is registered during Altibase Windows client installation procedure.
- Add a ODBC DSN for Altibase.
- example configuration :
[Altibase Connection Config]
Windows DSN Name: PYODBC
host(name or IP): 192.168.1.210
Port(default 20300): 21121
User: SYS
Password: MANAGER
Database: mydb
NLS_USE: UTF-8
Usage with Claude Desktop
- Install Claude for desktop.
uv
- Install uv
- uv is designed to be a fast and efficient alternative to pip and venv for Python package management and virtual environment creation.
MCP client configuration example without git clone
# Add the server to your claude_desktop_config.json
"mcpServers": {
"altibase": {
"command": "uvx",
"args": [
"mcp-server-altibase@latest",
"--odbc-dsn",
"PYODBC"
]
}
}
MCP client configuration example with git clone
# Add the server to your claude_desktop_config.json
"mcpServers": {
"altibase": {
"command": "uv",
"args": [
"--directory",
"path/to/repository/directory",
"run",
"mcp-server-altibase",
"--odbc-dsn",
"PYODBC"
]
}
}
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Metadata
Release files for mcp-server-altibase 0.0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| mcp_server_altibase-0.0.3.tar.gz | 23.3 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mcp_server_altibase-0.0.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 34.2 kB
Release files / mcp_server_altibase-0.0.3.tar.gz
| Download URL | mcp_server_altibase-0.0.3.tar.gz |
|---|---|
| Size | 23.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cb3e938e6e365974ff57bede43e2d951d0b98d50e916852b99b42c34c37693b3
|
|
BLAKE2b-256 checksum How to use checksums |
575f7bca677838b621f20221b3a86f1c3217e87358ddac68f6f2b047e76816c8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Release files / mcp_server_altibase-0.0.3-py3-none-any.whl
| Download URL | mcp_server_altibase-0.0.3-py3-none-any.whl |
|---|---|
| Size | 10.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8f41f87475ce5b615f0a013c33335f1ce5e68d2301d2f1d78ca98dfc175fb8a2
|
|
BLAKE2b-256 checksum How to use checksums |
2407dd833f42e4c6c51f5695a6eedbb6ab76e0f13c422757064e574d8b222de7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Security for mcp-server-altibase 0.0.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.