IBM watsonx.ai Granite runs on your own machine — the client starts it, so there is no endpoint to ping. 55 installs a week from npm. Last commit 8 Nov 2026.
IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.
We read the source, 1 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
'http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/token',
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const r = await redis.eval(
UPDATE destination_whitelist_settings
SET cooldown_seconds = ${ch.cooldown_seconds ?? row.cooldown_seconds},
const proc = spawn(ffmpegPath(), ['-hide_banner', '-loglevel', 'error', '-i', 'pipe:0', ...args, 'pipe:1']);
const raw = JSON.parse(await readFile(path.join(ROOT, dir, 'server.json'), 'utf8'));
lambda: subprocess.run(
if (reset) { state.cursor = null; state.total = 0; grid.innerHTML = skeletons(); stateEl.hidden = true; }
'UklGRmQBAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YUABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA…
const TELEGRAM_API = 'https://api.telegram.org';
COPY --parents package.json package-lock.json .npmrc* **/package.json /app/
const entries = await readdir(path.join(ROOT, parent), { withFileTypes: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch IBM watsonx.ai Granite and you get told the day something new turns up.
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 -e 'WATSONX_API_KEY=<WATSONX_API_KEY>' -- npx -y @three-ws/ibm-watsonx-mcp
{
"mcpServers": {
"ibm-watsonx": {
"command": "npx",
"args": [
"-y",
"@three-ws/ibm-watsonx-mcp"
],
"env": {
"WATSONX_API_KEY": "<WATSONX_API_KEY>"
}
}
}
}
[mcp_servers.ibm-watsonx]
command = "npx"
args = ["-y", "@three-ws/ibm-watsonx-mcp"]
env = { WATSONX_API_KEY = "<WATSONX_API_KEY>" }
{
"mcpServers": {
"ibm-watsonx": {
"command": "npx",
"args": [
"-y",
"@three-ws/ibm-watsonx-mcp"
],
"env": {
"WATSONX_API_KEY": "<WATSONX_API_KEY>"
}
}
}
}
{
"servers": {
"ibm-watsonx": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@three-ws/ibm-watsonx-mcp"
],
"env": {
"WATSONX_API_KEY": "<WATSONX_API_KEY>"
}
}
}
}
Put your own value in place of
<WATSONX_API_KEY> (IBM Cloud API key (create one at https://cloud.ibm.com/iam/apikeys)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
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).
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
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.
Pay-per-use IBM Granite AI via x402: chat, code, embeddings, forecasting. USDC on Base or Solana.
Run Together AI chat, embeddings and images; manage fine-tunes, batches and endpoints.
Answers built from our own checks of this server.