data-intelligence

data-intelligence-mcp-server is a centralized Model Context Protocol (MCP) server that provides a unified gateway for exposing and managing MCP tools across microservices in the Watsonx Data Intelligence ecosystem

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio ibm-data-intelligence-mcp-server uvx ibm-watsonx-data-intelligence-mcp-server --transport stdio \
  --env DI_APIKEY="Data Intelligence API key" \
  --env DI_ENV_MODE="Environment mode (SaaS or CPD)" \
  --env LOG_FILE_PATH="Path to log file (optional)" \
  --env DI_SERVICE_URL="Base URL for Watsonx Data Intelligence instance"

How to use

The Data Intelligence MCP Server provides a modular, standards-based interface that enables MCP clients (like Claude Desktop, VS Code Copilot, or Watsonx Orchestrate) to interact with IBM Data Intelligence services via the Model Context Protocol. It supports both stdio and HTTP/HTTPS transport, allowing local, screen-reader-friendly workflows as well as remote integrations. Tools and prompts for this server are documented in TOOLS_PROMPTS.md, and sample prompt templates are available in PROMPTS_TEMPLATE_SAMPLES to help you tailor interactions with Data Intelligence features such as data cataloging, model governance, and automation prompts. When using stdio, the MCP client communicates directly over standard input/output; in HTTP mode, the MCP Server acts as a typical web service behind a host/port and can be secured per your deployment requirements. This server can be integrated with Claude Desktop, VS Code Copilot, Watsonx Orchestrate, and IBM Bob to automate data-intelligence workflows.

How to install

Prerequisites:

Python 3.11 or higher
Access to IBM Data Intelligence SaaS or CPD 5.2.1
Optional: uv (for uvx-based transport)

Install from PyPI:

pip install ibm-watsonx-data-intelligence-mcp-server

Run via uvx in stdio mode (local setup):

uvx ibm-watsonx-data-intelligence-mcp-server --transport stdio

Run via uvx in http mode (remote setup):

uvx ibm-watsonx-data-intelligence-mcp-server

For CLI/IDE integrations (e.g., Claude Desktop or VS Code Copilot), configure the MCP server with the appropriate transport and environment variables as shown in the README examples.

Additional notes

Environment variables commonly required:

DI_SERVICE_URL: Base URL for Watsonx Data Intelligence (e.g., https://api.dataplatform.cloud.ibm.com)
DI_APIKEY: API key for Data Intelligence
DI_ENV_MODE: SaaS or CPD (default SaaS)
LOG_FILE_PATH: Optional path to a log file for debugging

Tips:

Use stdio mode for local development and testing; switch to http/https mode for remote deployments behind a reverse proxy or API gateway.
When using http/https, ensure proper authentication headers are configured in the client configuration and that TLS/SSL certificates are valid in your environment.
If you upgrade the MCP server, verify that client configurations (CLI/UI integrations) remain compatible with the new transport settings.
Refer to TOOLS_PROMPTS.md for the supported tools and sample prompts to tailor interactions with IBM Data Intelligence services.

Related MCP Servers

mcp-vegalite

MCP server from isaacwasserman/mcp-vegalite-server

github-chat

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

nautex

MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline

pagerduty

PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.

futu-stock

mcp server for futuniuniu stock

mcp -boilerplate

Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP