We are excited to announce the public preview release of the IBM watsonx.data integration MCP Server. This MCP server enables you to connect your data integration workflows directly to your AI Agent of choice. Whether it’s IBM Bob, Codex, Claude or another compatible Agent, you can now build, manage and optimize your pipelines entirely through natural language. This MCP server comes with 3 skills out of the box (Platform, Streaming, Batch skills).

What can you do with our MCP server?

• Natural Language Pipeline building: Create, modify, manage, and optimize your pipelines in natural language.

• Pipeline Explainability: Generate end to end summaries of complex data flows.

• On Demand Documentation: Get instant lists of required fields and preconditions for any stage.

• SDK Code Generation: Generate SDK automation scripts (bulk editing pipelines) in natural language

• Pipeline Healing: Identify pipeline failures and recommend or apply configuration fixes.

• Job Operations: Monitor job statuses and promote pipelines across environments via chat.

• Admin Automation: Automate project access and user management through simple chat requests.

• Super charge your Agents: Give your agents access to data pipelines so they can autonomously orchestrate complex data workflows.

Getting Started with the IBM watsonx.data integration MCP Server

Requirements

Python 3.12

Setup

There are three ways to run this MCP server. Choose the option that best fits your environment.

Option 1 Using uvx (Recommended)

The fastest way to get started with no installation required.

If you do not have uvx, install it first:

pip install uv

Verify it works:

uvx --python 3.12 --from ibm_watsonx_data_integration_mcp data-intg-mcp --help

MCP Server Configuration:

{
  "mcpServers": {
    "data-intg-mcp": {
      "command": "uvx",
      "args": [
        "--python",
        "3.12",
        "--from",
        "ibm_watsonx_data_integration_mcp",
        "data-intg-mcp"
      ],
      "env": {
        "WATSONX_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Option 2 Using uv as a Tool

If you do not have uv, install it first:

pip install uv

Install:

uv tool install --python 3.12 ibm_watsonx_data_integration_mcp

Verify installation:

data-intg-mcp --help

MCP Server Configuration:

{
  "mcpServers": {
    "data-intg-mcp": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "data-intg-mcp"
      ],
      "env": {
        "WATSONX_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Option 3 Using pip with a Virtual Environment

Install:

python3.12 -m venv .venv
source .venv/bin/activate
pip install ibm_watsonx_data_integration_mcp

Verify installation:

data-intg-mcp --help

MCP Server Configuration:

{
  "mcpServers": {
    "data-intg-mcp": {
      "command": "<Path to .venv>/bin/data-intg-mcp",
      "args": [],
      "env": {
        "WATSONX_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

AI Agent Client Integration

Claude Desktop

Navigate to Claude, select Settings → go to Developer, and select Edit Config. Add one of the MCP server configurations above to your claude_desktop_config.json file.

Bob (VS Code)

Navigate to VS Code, Open Bob, select Settings, go to MCP, and select Open Global MCPs. Add one of the MCP server configurations above to your Bob MCP config file.

Authentication

Set your WATSONX_API_KEY in the env block of your MCP client configuration. The server validates this key on startup.

Try it free

Create a free trial of watsonx.data integration and try out our MCP server today!