IBM watsonx.ai Granite runs on your own machine — the client starts it, so there is no endpoint to ping. 50 installs a week from npm. Last commit 22 Sep 2026.
IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.
Today is the operative word: we check IBM watsonx.ai Granite every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ibm-watsonx -- npx -y @three-ws/ibm-watsonx-mcp
{
"mcpServers": {
"ibm-watsonx": {
"args": [
"-y",
"@three-ws/ibm-watsonx-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.ibm-watsonx]
command = "npx"
args = ["-y", "@three-ws/ibm-watsonx-mcp"]
{
"mcpServers": {
"ibm-watsonx": {
"args": [
"-y",
"@three-ws/ibm-watsonx-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ibm-watsonx": {
"args": [
"-y",
"@three-ws/ibm-watsonx-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
WATSONX_API_KEY (IBM Cloud API key (create one at https://cloud.ibm.com/iam/apikeys).), WATSONX_PROJECT_ID (watsonx.ai project id (Project → Manage → General → Project ID). Provide this or WATSONX_SPACE_ID.), WATSONX_SPACE_ID (watsonx.ai deployment space id. Alternative to WATSONX_PROJECT_ID.), WATSONX_URL (Regional inference host. Defaults to https://us-south.ml.cloud.ibm.com.), WATSONX_MODEL_ID (Default chat/generation model id. Defaults to ibm/granite-3-8b-instruct.), WATSONX_EMBED_MODEL_ID (Default embedding model id. Defaults to ibm/granite-embedding-278m-multilingual.), WATSONX_API_VERSION (watsonx.ai REST API version date. Defaults to 2024-05-31.).
The author declared them in the registry entry; get the values from the project itself.
MCP server for GigaChat — AI chat, embeddings, image generation (Russia)
MCP server for the xAI Grok API — chat, vision, search, and embeddings
Search the web, generate AI responses, and create embeddings with real-time information
MCP server for the OpenAI ChatGPT API — chat, vision, and embeddings
x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
Pay-per-use IBM Granite AI via x402: chat, code, embeddings, forecasting. USDC on Base or Solana.
Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
Answers built from our own checks of this server.