home / mcp / ibm cloud object storage mcp server

IBM Cloud Object Storage MCP Server

This read-only MCP Server allows you to connect to IBM Cloud Object Storage data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for IBM Cloud Object Storage (https://www.cdata.com/drivers/ibmcloudobjectstorage/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-ibm-cloud-object-storage-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/ibm-cloud-object-storage.prp"
      ]
    }
  }
}

You can query live data from IBM Cloud Object Storage through a read-only MCP server. This server wraps the CData JDBC Driver to expose IBM Cloud Object Storage as relational-like data sources you can ask natural-language questions about, without writing SQL. It is designed to be easy to set up and to work with MCP clients that run locally on your machine.

How to use

After you have the MCP server up and running, you will interact with it through an MCP client on your machine. Use natural language prompts to query IBM Cloud Object Storage data. Examples include asking for the current state of storage usage, listing objects in a bucket, or querying metadata about stored items. The server provides tools that expose tables, columns, and the ability to run queries so you can retrieve exactly the data you need without writing SQL.

How to install

Prerequisites: you need Java installed to run the MCP server. You also need Maven to build the server from source and the CData JDBC Driver for IBM Cloud Object Storage to connect to your data.

# 1) Clone the project
git clone https://github.com/cdatasoftware/ibm-cloud-object-storage-mcp-server-by-cdata.git
cd ibm-cloud-object-storage-mcp-server-by-cdata

# 2) Build the server
mvn clean install
# This creates the JAR: CDataMCP-jar-with-dependencies.jar

Configure and run the MCP server

Install the CData JDBC Driver for IBM Cloud Object Storage, license it, and configure a JDBC connection. You will create a .prp file with your connection details, then run the MCP server using that file.

# License the driver (example path for Windows)
java -jar cdata.jdbc.ibmcloudobjectstorage.jar --license

# Run the Connection String utility to create a connection string
java -jar cdata.jdbc.ibmcloudobjectstorage.jar

Run the MCP server

Start the MCP server on its own so it can expose the IBM Cloud Object Storage data to your MCP client. Use the final start command shown here, replacing paths with your actual locations.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/ibm-cloud-object-storage.prp
```
Note: The server runs with stdio, so it must be on the same machine as the client.

Security and configuration notes

Keep your JDBC driver license and connection details secure. The JDBC connection string and prp file contain sensitive information. Store them in a secure location and restrict access to trusted users.

Troubleshooting

If you cannot see or access the MCP server from your client, ensure you have fully quit and restarted your MCP client after starting the server. Verify your ibm-cloud-object-storage.prp file contains the correct JdbcUrl and that the DriverPath points to the exact driver JAR you installed.

License and usage notes

This MCP server is provided under the MIT License. You may use, modify, and distribute it in accordance with the terms of that license.

Notes about data sources and tools

The MCP server exposes tools to discover data structure and run queries. You can list available tables, fetch column details for a table, and execute read-only queries against IBM Cloud Object Storage.

Available tools

source_get_tables

Retrieves a list of tables available in the data source. The output is returned in CSV format with column headers.

source_get_columns

Retrieves a list of columns for a table. The output is CSV with headers.

source_run_query

Executes a SQL SELECT query against the exposed data source.