LABSCO SUMMARY

Object storage, addressed as rows.

Storage questions are usually shaped like queries — what is in this bucket, how big, how old, changed by whom — and the console makes you browse for them instead. The driver flattens buckets and object metadata into tables, so the assistant can aggregate rather than page. It reads only: nothing here uploads, moves or deletes an object. Setup is a Maven build, a licensed driver and a property file.

What it is

A local, read-only bridge between an assistant and IBM Cloud Object Storage. CData's JDBC driver exposes IBM Cloud Object Storage as relational SQL models; this server wraps the driver so a model can discover the tables and query them, and you can ask in plain language instead of writing SQL. It runs over stdio, so the client has to be on the same machine.

What you get

get_tables lists the tables the driver exposes, returned as CSV with a header row
get_columns lists the columns on one of those tables, in the same CSV shape
run_query executes a SQL SELECT against live IBM Cloud Object Storage data
Tool names carry the prefix you set in the property file — the sample config uses Prefix=ibmcloudobjectstorage
A Tables setting that only picks which tables also get a ready-made description (blank means none); it does not limit what the tools can list or query, so limit the connection or the account it signs in with

Requirements

Java and Maven: mvn clean install builds CDataMCP-jar-with-dependencies.jar. Separately install the CData JDBC Driver for IBM Cloud Object Storage and license it by running java -jar cdata.jdbc.ibmcloudobjectstorage.jar --license, entering TRIAL or a license key. Build the connection string with the same jar, authenticating in the browser if the source uses OAuth, then write a .prp file naming the driver path, the driver class cdata.jdbc.ibmcloudobjectstorage.IBMCloudObjectStorageDriver and that JDBC URL. Point your client at java -jar with the built jar and the .prp file.

Setup effort

Build from source — clone the repository, then point your client at the binary

See installation options

USE CASES

01

Finding out what the storage account exposes

List the tables the driver publishes, then the columns on the one you need.

02

Answering a question about bucket contents

Ask in plain language; the assistant writes the SELECT and reads the CSV back.

03

Auditing what is stored and how much of it

Query object metadata directly instead of browsing the console.

3 tools

Listed in project docs. Your client may show a different list.

ibmcloudobjectstorage_get_tables

ibmcloudobjectstorage_get_columns

ibmcloudobjectstorage_run_query

BEFORE YOU INSTALL

What to know first

Tools you get

3 tools named in the project's documentation. Tool names start with the Prefix in the .prp file, so the README's Prefix=ibmcloudobjectstorage gives ibmcloudobjectstorage_get_tables, ibmcloudobjectstorage_get_columns and ibmcloudobjectstorage_run_query.

Where it runs

Both documented setups run the server on your machine.

INSTALLATION

Connect your client

Clone the repository, then point your client at the binary. This one is built from source rather than installed with a single command.

Server setup

TERMINAL

git clone https://github.com/cdatasoftware/ibm-cloud-object-storage-mcp-server-by-cdata.git
cd ibm-cloud-object-storage-mcp-server-by-cdata
mvn clean install

Download and install the CData JDBC Driver for IBM Cloud Object Storage from https://www.cdata.com/drivers/ibmcloudobjectstorage/download/jdbc

License the driver: java -jar cdata.jdbc.ibmcloudobjectstorage.jar --license (enter name, email, and "TRIAL" or a license key)

Run java -jar cdata.jdbc.ibmcloudobjectstorage.jar with no arguments to open the Connection String utility, test the connection, copy the connection string

Create ibm-cloud-object-storage.prp with:

FILE · ibm-cloud-object-storage.prp

Prefix=ibmcloudobjectstorage
ServerName=CDataIBMCloudObjectStorage
ServerVersion=1.0
DriverPath=<YOUR_DRIVER_PATH>
DriverClass=cdata.jdbc.ibmcloudobjectstorage.IBMCloudObjectStorageDriver
JdbcUrl=<YOUR_JDBC_URL>
Tables=

Tables only picks which tables also get a ready-made description for your assistant, and empty means none; the server can still list and query every table your connection string reaches, so to keep data out of reach, limit that connection or the account it signs in with.

Add the mcpServers entry below to claude_desktop_config.json, pointing java at CDataMCP-jar-with-dependencies.jar and at the .prp file, then fully quit and reopen the client

MCP Clients

Claude Desktop — Windows, macOS, Linux

JSON

{
  "mcpServers": {
    "ibm-cloud-object-storage": {
      "command": "<YOUR_PATH_TO_JAVA>",
      "args": [
        "-jar",
        "<YOUR_PATH_TO_CDATA_MCP_JAR_WITH>",
        "<YOUR_PATH_TO_IBM_CLOUD_OBJECT_STORAGE>"
      ]
    }
  }
}

CData IBM Cloud Object Storage