IBM watsonx.ai Granite

Name: IBM watsonx.ai Granite
Author: nirholas

by nirholasversion 0.2.2i★ –iRuns on your computer

Registry nameio.github.nirholas/ibm-watsonx

Install

Overview

Description from the maker (original English)

IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Chat & email
You need to fill in: WATSONX_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: WATSONX_API_KEY, WATSONX_PROJECT_ID, WATSONX_SPACE_ID, WATSONX_URL, WATSONX_MODEL_ID, WATSONX_EMBED_MODEL_ID, WATSONX_API_VERSION

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "ibm-watsonx": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/ibm-watsonx-mcp"
      ],
      "env": {
        "WATSONX_API_KEY": "your-value",
        "WATSONX_PROJECT_ID": "your-value",
        "WATSONX_SPACE_ID": "your-value",
        "WATSONX_URL": "your-value",
        "WATSONX_MODEL_ID": "your-value",
        "WATSONX_EMBED_MODEL_ID": "your-value",
        "WATSONX_API_VERSION": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add ibm-watsonx --env WATSONX_API_KEY=your-value --env WATSONX_PROJECT_ID=your-value --env WATSONX_SPACE_ID=your-value --env WATSONX_URL=your-value --env WATSONX_MODEL_ID=your-value --env WATSONX_EMBED_MODEL_ID=your-value --env WATSONX_API_VERSION=your-value -- npx -y @three-ws/ibm-watsonx-mcp

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "ibm-watsonx": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/ibm-watsonx-mcp"
      ],
      "env": {
        "WATSONX_API_KEY": "your-value",
        "WATSONX_PROJECT_ID": "your-value",
        "WATSONX_SPACE_ID": "your-value",
        "WATSONX_URL": "your-value",
        "WATSONX_MODEL_ID": "your-value",
        "WATSONX_EMBED_MODEL_ID": "your-value",
        "WATSONX_API_VERSION": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "ibm-watsonx": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/ibm-watsonx-mcp"
      ],
      "env": {
        "WATSONX_API_KEY": "your-value",
        "WATSONX_PROJECT_ID": "your-value",
        "WATSONX_SPACE_ID": "your-value",
        "WATSONX_URL": "your-value",
        "WATSONX_MODEL_ID": "your-value",
        "WATSONX_EMBED_MODEL_ID": "your-value",
        "WATSONX_API_VERSION": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

WATSONX_API_KEY secret required env
IBM Cloud API key (create one at https://cloud.ibm.com/iam/apikeys).
WATSONX_PROJECT_ID env
watsonx.ai project id (Project → Manage → General → Project ID). Provide this or WATSONX_SPACE_ID.
WATSONX_SPACE_ID env
watsonx.ai deployment space id. Alternative to WATSONX_PROJECT_ID.
WATSONX_URL env
Regional inference host. Defaults to https://us-south.ml.cloud.ibm.com.
WATSONX_MODEL_ID env
Default chat/generation model id. Defaults to ibm/granite-3-8b-instruct.
WATSONX_EMBED_MODEL_ID env
Default embedding model id. Defaults to ibm/granite-embedding-278m-multilingual.
WATSONX_API_VERSION env
watsonx.ai REST API version date. Defaults to 2024-05-31.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account nirholas, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Chat & emaili

More stars than 0% of the other 1777 servers in this category
Published to the registry more recently than 49% of the other 1777 servers in this category
Basic checks equal to or better than 100% of the other 1777 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is IBM watsonx.ai Granite safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: WATSONX_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.2) reached the registry 27 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: Vexa, emailmd, MCP WhatsApp Cloud

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Vexa

by Vexa-ai

Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.

Runs in the cloud★ 2,949Apache-2.0Updated 2 months ago

Install

emailmd

by anypost

Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.

Computer or cloud★ 1,385MITUpdated 31 days ago

Install

MCP WhatsApp Cloud

by codespar

MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API

Runs on your computer★ 277MITUpdated 5 months ago

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

@three-ws/ibm-watsonx-mcp

MCP server for IBM watsonx.ai — chat, generation, embeddings, tokenization, forecasting, and model discovery, on your own IBM Cloud account.

Install · Quick start · Tools · Requirements · three.ws

A Model Context Protocol server that exposes IBM watsonx.ai — IBM Granite foundation models and anything else in your account — to MCP clients such as Claude Desktop, Claude Code, and Cursor. It talks directly to the watsonx.ai as-a-Service REST API with your own IBM Cloud credentials: it mints an IAM bearer token from your API key, caches it until just before expiry, and scopes every call to your project. No intermediary backend, no telemetry, no mock data.

Community-built and not affiliated with IBM. Registry name: io.github.nirholas/ibm-watsonx.

Install

npm install @three-ws/ibm-watsonx-mcp

Run it directly with npx (no install needed):

WATSONX_API_KEY=... WATSONX_PROJECT_ID=... npx @three-ws/ibm-watsonx-mcp

Or install globally to get the ibm-watsonx-mcp binary on your PATH:

npm install -g @three-ws/ibm-watsonx-mcp

Quick start

With Claude Code, one command:

claude mcp add ibm-watsonx -e WATSONX_API_KEY=... -e WATSONX_PROJECT_ID=... -- npx -y @three-ws/ibm-watsonx-mcp

Or add the server to your MCP client config (claude_desktop_config.json, Cursor's mcp.json):

"mcpServers": { "ibm-watsonx": { "command": "npx", "args": ["-y", "@three-ws/ibm-watsonx-mcp"], "env": { "WATSONX_API_KEY": "your-ibm-cloud-api-key", "WATSONX_PROJECT_ID": "your-watsonx-project-id" } } } }

Restart the client and the six tools below appear. Inspect the surface manually with the MCP Inspector:

npx -y @modelcontextprotocol/inspector npx @three-ws/ibm-watsonx-mcp

Tools

Tool	What it does
`watsonx_chat`	Chat completion from a list of role/content messages. Returns the reply plus token usage.
`watsonx_generate`	Raw prompt completion with decoding control (greedy/sample, stop sequences).
`watsonx_embed`	Embedding vectors for one or more texts (up to 1000). One vector per input plus dimensionality.
`watsonx_tokenize`	Token count (and optionally the tokens) for a text against a model tokenizer.
`watsonx_forecast`	Zero-shot time-series forecasting with an IBM Granite TimeSeries (TinyTimeMixer) model.
`watsonx_list_models`	List the foundation models available to your account and region, optionally filtered.

Every tool is a read-only model-inference call — nothing in your environment or IBM account is modified — and declares MCP tool annotations (readOnlyHint, openWorldHint, idempotentHint) so clients can reason about side effects.

Input parameters

`watsonx_chat` — messages (required: array of { role, content }, roles system/user/assistant), model, max_tokens (1–4096), temperature (0–2), top_p (0–1).

`watsonx_generate` — input (required), model, max_new_tokens (1–4096), temperature (0–2), decoding_method (greedy/sample), stop_sequences.

`watsonx_embed` — inputs (required: 1–1000 texts), model.

`watsonx_tokenize` — input (required), model, return_tokens (boolean).

`watsonx_forecast` — timestamps (required: ISO-8601, uniform cadence, oldest first), values (required: numeric, same length), freq (required: pandas cadence, e.g. 1h, 15min, 1D), model, target_column, prediction_length (1–96).

`watsonx_list_models` — filter (e.g. function_text_generation, function_embedding), limit (1–200, default 100).

Example calls

// watsonx_chat

{ "messages": [{ "role": "user", "content": "Explain MCP in one sentence." }] }

// watsonx_generate { "input": "Write a haiku about Kubernetes.", "decoding_method": "sample", "temperature": 0.7, "max_new_tokens": 60 }

// watsonx_embed { "inputs": ["lakehouse", "data warehouse"] }

// watsonx_forecast { "timestamps": ["2025-01-01T00:00:00Z", "2025-01-01T01:00:00Z"], "values": [1200, 1180], "freq": "1h", "prediction_length": 24 }

// watsonx_list_models { "filter": "function_embedding" }

How auth works

WATSONX_API_KEY is exchanged for a short-lived IAM bearer token at https://iam.cloud.ibm.com/identity/token (grant_type=urn:ibm:params:oauth:grant-type:apikey). The token is cached in-process and refreshed about five minutes before it expires. Your API key never leaves your machine except in that single IAM exchange.

Requirements

Node.js >= 20.
An IBM Cloud account with watsonx.ai provisioned — sign up (free tier available).
An IBM Cloud API key — create one at https://cloud.ibm.com/iam/apikeys.
Your watsonx.ai project id — open the project → Manage → General → Project ID (or a deployment space id).

Environment variables

Variable	Required	Default
`WATSONX_API_KEY`	yes	—
`WATSONX_PROJECT_ID`	yes (or `WATSONX_SPACE_ID`)	—
`WATSONX_SPACE_ID`	alternative to `WATSONX_PROJECT_ID`	—
`WATSONX_URL`	no	`https://us-south.ml.cloud.ibm.com`
`WATSONX_MODEL_ID`	no	`ibm/granite-3-8b-instruct`
`WATSONX_EMBED_MODEL_ID`	no	`ibm/granite-embedding-278m-multilingual`
`WATSONX_FORECAST_MODEL`	no	`ibm/granite-ttm-512-96-r2`
`WATSONX_API_VERSION`	no	`2024-05-31`
`WATSONX_TS_API_VERSION`	no	`2025-02-11` (time-series API date)
`WATSONX_TIMEOUT_MS`	no	`60000`
`WATSONX_IAM_URL`	no	`https://iam.cloud.ibm.com/identity/token`

Regional hosts: us-south, eu-de, eu-gb, jp-tok, au-syd, ca-tor — e.g. https://eu-de.ml.cloud.ibm.com.

@three-ws/ibm-x402-mcp — the same IBM Granite tools as pay-per-use x402 endpoints (USDC on Solana), so callers need no IBM account of their own.

IBM watsonx.ai Granite

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Chat & emaili

Common questions

Alternatives

Vexa

emailmd

MCP WhatsApp Cloud

README from the maker

Install

Quick start

Tools

Input parameters

Example calls

How auth works

Requirements

Environment variables

Related

Links