<h1 align="center">
<a href="https://prompts.chat">
[](https://npmjs.com/package/@purplesquirrel/watsonx-mcp-server)
Sign in to like and favorite skills
MCP server for IBM watsonx.ai integration with Claude Code. Enables Claude to delegate tasks to IBM's foundation models (Granite, Llama, Mistral, etc.).
| Tool | Description |
|---|---|
| Generate text using watsonx.ai models |
| Chat with watsonx.ai models |
| Generate text embeddings |
| List available models |
cd ~/watsonx-mcp-server npm install
Set these environment variables:
WATSONX_API_KEY=your-ibm-cloud-api-key WATSONX_URL=https://us-south.ml.cloud.ibm.com WATSONX_SPACE_ID=your-deployment-space-id # Recommended: deployment space WATSONX_PROJECT_ID=your-project-id # Alternative: project ID
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.
The MCP server is already configured in
~/.claude.json:
{ "mcpServers": { "watsonx": { "type": "stdio", "command": "node", "args": ["/Users/matthewkarsten/watsonx-mcp-server/index.js"], "env": { "WATSONX_API_KEY": "your-api-key", "WATSONX_URL": "https://us-south.ml.cloud.ibm.com", "WATSONX_SPACE_ID": "your-deployment-space-id" } } } }
Once configured, Claude can use watsonx.ai tools:
User: Use watsonx to generate a haiku about coding Claude: [Uses watsonx_generate tool] Result: Code flows like water Bugs arise, then disappear Programs come alive
Some notable models available:
ibm/granite-3-3-8b-instruct - IBM Granite 3.3 8B (recommended)ibm/granite-13b-chat-v2 - IBM Granite chat modelibm/granite-3-8b-instruct - Granite 3 instruct modelmeta-llama/llama-3-70b-instruct - Meta's Llama 3 70Bmistralai/mistral-large - Mistral AI large modelibm/slate-125m-english-rtrvr-v2 - Embedding modelUse
watsonx_list_models to see all available models.
Claude Code (Opus 4.5) │ └──▶ watsonx MCP Server │ └──▶ IBM watsonx.ai API │ ├── Granite Models ├── Llama Models ├── Mistral Models └── Embedding Models
This enables a two-agent architecture where:
Claude can delegate tasks to watsonx.ai when:
This MCP server uses:
Create your own watsonx.ai project and deployment space in IBM Cloud.
This watsonx MCP server works alongside the IBM Z MCP server:
Claude Code (Opus 4.5) │ ├──▶ watsonx MCP Server │ └── Text generation, embeddings, chat │ └──▶ ibmz MCP Server └── Key Protect HSM, z/OS Connect
Demo scripts in the ibmz-mcp-server:
demo-full-stack.js - Full 5-service pipelinedemo-rag.js - RAG with watsonx embeddings + GraniteThe document analyzer (
document-analyzer.js) provides powerful tools for analyzing your external drive data using watsonx.ai:
# View document catalog (9,168 documents) node document-analyzer.js catalog # Summarize a document node document-analyzer.js summarize 1002519.txt # Analyze document type, topics, entities node document-analyzer.js analyze 1002519.txt # Ask questions about a document node document-analyzer.js question 1002519.txt 'What AWS credentials are needed?' # Generate embeddings for documents node document-analyzer.js embed # Semantic search across documents node document-analyzer.js search 'IBM Cloud infrastructure'
Run the full demo:
./demo-external-drive.sh
The
embedding-index.js tool provides semantic search and RAG (Retrieval Augmented Generation):
# Build an embedding index (50 documents) node embedding-index.js build 50 # Semantic search node embedding-index.js search 'cloud infrastructure' # RAG query - retrieves relevant docs and generates answer node embedding-index.js rag 'How do I set up AWS for Satellite?' # Show index statistics node embedding-index.js stats
The
batch-processor.js tool processes multiple documents at once:
# Classify documents into categories node batch-processor.js classify 20 # Extract topics from documents node batch-processor.js topics 15 # Generate one-line summaries node batch-processor.js summarize 10 # Full analysis (classify + topics + summary) node batch-processor.js full 10
Categories: technical, business, creative, personal, code, legal, marketing, educational, other
index.js - MCP server implementationdocument-analyzer.js - Document analysis CLI toolembedding-index.js - Embedding index and RAG toolbatch-processor.js - Batch document processordemo-external-drive.sh - Demo scriptpackage.json - DependenciesREADME.md - This fileMatthew Karsten
MIT
If this MCP server is useful to you, consider supporting its development:
Enterprise support available - Contact us for SLAs, custom development, and priority support.