watsonx MCP Server

MCP server for IBM watsonx.ai integration with Claude Code. Enables Claude to delegate tasks to IBM's foundation models (Granite, Llama, Mistral, etc.).

Features

• Text Generation - Generate text using watsonx.ai foundation models

• Chat - Have conversations with watsonx.ai chat models

• Embeddings - Generate text embeddings

• Model Listing - List all available foundation models

Available Tools

Setup

1. Install Dependencies

2. Configure Environment

Set these environment variables:

Note: Either WATSONX_SPACE_ID or WATSONX_PROJECT_ID is required for text generation, embeddings, and chat. Deployment spaces are recommended as they have Watson Machine Learning (WML) pre-configured.

3. Add to Claude Code

The MCP server is already configured in ~/.claude.json:

Usage

Once configured, Claude can use watsonx.ai tools:

Available Models

Some notable models available:

• ibm/granite-3-3-8b-instruct - IBM Granite 3.3 8B (recommended)

• ibm/granite-13b-chat-v2 - IBM Granite chat model

• ibm/granite-3-8b-instruct - Granite 3 instruct model

• meta-llama/llama-3-70b-instruct - Meta's Llama 3 70B

• mistralai/mistral-large - Mistral AI large model

• ibm/slate-125m-english-rtrvr-v2 - Embedding model

Use watsonx_list_models to see all available models.

Architecture

Two-Agent System

This enables a two-agent architecture where:

1. Claude (Opus 4.5) - Primary reasoning agent, handles complex tasks

2. watsonx.ai - Secondary agent for specific workloads

Claude can delegate tasks to watsonx.ai when:

• IBM-specific model capabilities are needed

• Running batch inference on enterprise data

• Using specialized Granite models

• Generating embeddings for RAG pipelines

IBM Cloud Resources

This MCP server uses:

• Service: watsonx.ai Studio (data-science-experience)

• Plan: Lite (free tier)

• Region: us-south

Create your own watsonx.ai project and deployment space in IBM Cloud.

Integration with IBM Z MCP Server

This watsonx MCP server works alongside the IBM Z MCP server:

Demo scripts in the ibmz-mcp-server:

• demo-full-stack.js - Full 5-service pipeline

• demo-rag.js - RAG with watsonx embeddings + Granite

Document Analyzer

The document analyzer (document-analyzer.js) provides powerful tools for analyzing your external drive data using watsonx.ai:

Commands

Features

• Summarization: Generate concise summaries of any document

• Analysis: Extract document type, topics, entities, and sentiment

• Q&A: Ask natural language questions about document content

• Embeddings: Generate 768-dimensional vectors for semantic search

• Semantic Search: Find similar documents using vector similarity

Demo

Run the full demo:

Embedding Index & RAG

The embedding-index.js tool provides semantic search and RAG (Retrieval Augmented Generation):

Batch Processor

The batch-processor.js tool processes multiple documents at once:

Categories: technical, business, creative, personal, code, legal, marketing, educational, other

Files

• index.js - MCP server implementation

• document-analyzer.js - Document analysis CLI tool

• embedding-index.js - Embedding index and RAG tool

• batch-processor.js - Batch document processor

• demo-external-drive.sh - Demo script

• package.json - Dependencies

• README.md - This file

Author

Matthew Karsten

License

MIT