IBM Cloud Object Storage MCP Server by CData

@CDataSoftware

Basic information

About IBM Cloud Object Storage MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for IBM Cloud Object Storage (beta): https://www.cdata.com/download/download.aspx?sku=GMZK-V&type=beta

#ibm-cloud#object-storage #mcp-server

IBM Cloud Object Storage MCP Server by CData config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "{classname_dash}": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\ibm-cloud-object-storage.prp"
      ]
    }
  }
}

IBM Cloud Object Storage MCP Server by CData tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is IBM Cloud Object Storage MCP Server by CData?

This is a read-only MCP (Model Context Protocol) server that allows LLMs like Claude Desktop to query live data from IBM Cloud Object Storage. It wraps the CData JDBC Driver for IBM Cloud Object Storage and exposes relational SQL models through a simple MCP interface, enabling natural language queries without SQL.

How to use IBM Cloud Object Storage MCP Server by CData?

Clone the repository, build the JAR with Maven, download and license the CData JDBC Driver, configure a connection string using the driver’s utility, create a .prp file with JDBC properties, and add the server to your Claude Desktop config file (claude_desktop_config.json). The server runs via java -jar using stdio transport.

Key features of IBM Cloud Object Storage MCP Server by CData

Read-only access to IBM Cloud Object Storage data
Exposes data as relational SQL tables
Provides tools: get_tables, get_columns, run_query
Supports natural language queries through AI clients
Uses OAuth authentication if required
Runs locally on the same machine as the client

Use cases of IBM Cloud Object Storage MCP Server by CData

Ask an LLM to summarize bucket contents or file metadata
Query storage logs or object metadata without writing SQL
Combine IBM Cloud Object Storage data with other data sources in a conversational interface
Enable non-technical users to explore stored data via chat

Frequently asked questions

Is this server read-only?

Yes. The server only supports SELECT queries. For full read, write, update, and delete capabilities, see CData’s beta MCP Server for IBM Cloud Object Storage.

What are the runtime requirements?

Java (to run the JAR) and the CData JDBC Driver for IBM Cloud Object Storage (must be downloaded and licensed separately).

How does the server connect to IBM Cloud Object Storage?

It uses a JDBC connection string configured via the CData JDBC Driver’s connection string utility. OAuth authentication is supported.

What transport does the server use?

The server uses stdio transport, so it must run on the same machine as the MCP client (e.g., Claude Desktop).

Where does the data live?

Data remains in IBM Cloud Object Storage; the server queries it live and does not store a copy locally.

Comments

More Files & Storage MCP servers

mcp-rquest

xxxbrian

A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.

HTMLvault

AI tools (Claude, ChatGPT, Gemini, Grok, etc.) generate HTML constantly, from reports to landing pages to prototypes, but there's no easy way to share it or know if anyone looked. HTMLvault turns any HTML into a clean, t

Filesystem MCP Server

cyanheads

A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal

PDF Reader MCP Server (@sylphlab/pdf-reader-mcp)

sylphlab

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

shtse8

810