How do I connect this MCP to my AI client?

You connect through Vinkius. Once you subscribe, you can add the MCP to any compatible client like Claude, Cursor, or Windsurf with one click.

Do I need my own IBM watsonx account?

Yes, this MCP requires you to provide your own IBM watsonx credentials to access your specific projects and models.

Can I run model tuning through my agent?

Yes, you can use the start_model_tuning capability to begin a job and get_tuning_status to track it.

What kind of models can I access?

You can access any foundation models available in your watsonx account by using the list_models capability.

Is this MCP hosted by Vinkius?

Yes, Vinkius hosts and manages the MCP, so you don't have to worry about running the connection yourself.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect IBM watsonx to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Bring enterprise-grade foundation models to your local AI client.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through IBM watsonx.

01
Create prompt
This capability creates a new prompt within your watsonx environment.
02
Generate chat
Use this to produce chat completions from a watsonx chat model for conversational applications.
03
Generate embeddings
This capability generates vector embeddings for input text to support similarity searches or semantic analysis.
04
Get model details
Get specific technical specifications for a chosen foundation model.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through IBM watsonx.

05
List models
This capability returns a list of available foundation models, including their IDs, families, and lifecycle states.
06
Get tuning status
Check the current progress and status of a specific prompt tuning job.
07
List projects
Retrieve a list of all watsonx projects associated with your account.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through IBM watsonx.

08
List prompts
This capability pulls a list of all saved prompts within a specific watsonx project.
09
Start model tuning
Initiate a prompt tuning job for a foundation model using training data from a cloud storage URL.
10
Generate text
Use this to generate single-turn text for tasks like summarization or content creation.

Real work

What teams actually run

Automated Content Generation

An agent uses generate_text to produce summaries of long documents stored in watsonx.

Semantic Search Implementation

A developer uses generate_embeddings to build a searchable vector database from text inputs.

Model Optimization

A data scientist triggers start_model_tuning to refine a model's performance on specific datasets.

Conversational Bot Development

An engineer uses generate_chat to power multi-turn dialogue in a custom application.

Automate a task

Put IBM watsonx to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

IBM watsonx works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put IBM watsonx to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

972ms average. Fast in production.

IBM watsonx is checked daily against the live service.

Daily averagePeak 1140ms

Oct 3Today

Fastest day: 795ms
Slowest day: 1140ms
14-day trend: Slowing+23%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of IBM watsonx, so you can see the experience inside your AI.

It does not authenticate your account with IBM watsonx. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

IBM watsonx Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_gXytFT8fNy6ELfNWb5ZhGBzw4TcaHPZqjIMO9o5b/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — IBM watsonx capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "ibm-watsonx-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_gXytFT8fNy6ELfNWb5ZhGBzw4TcaHPZqjIMO9o5b/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up IBM watsonx in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work IBM watsonx owners hand off.

This MCP is built for developers and data scientists working within the IBM ecosystem who want to control enterprise models through an AI agent.

01
AI Engineers
They use the MCP to automate model tuning and embedding generation.
02
Data Scientists
They use it to manage projects and inspect model specifications.
03
Software Developers
They use it to integrate watsonx text generation into their applications.

FAQ

Questions IBM watsonx owners ask.

01
How do I connect this MCP to my AI client?
You connect through Vinkius. Once you subscribe, you can add the MCP to any compatible client like Claude, Cursor, or Windsurf with one click.
02
Do I need my own IBM watsonx account?
Yes, this MCP requires you to provide your own IBM watsonx credentials to access your specific projects and models.
03
Can I run model tuning through my agent?
Yes, you can use the start_model_tuning capability to begin a job and get_tuning_status to track it.
04
What kind of models can I access?
You can access any foundation models available in your watsonx account by using the list_models capability.
05
Is this MCP hosted by Vinkius?
Yes, Vinkius hosts and manages the MCP, so you don't have to worry about running the connection yourself.

Explore

More in Industry Titans

Connect IBM watsonx to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create prompt

Generate chat

Generate embeddings

Get model details

05-07

List models

Get tuning status

List projects

08-10

List prompts

Start model tuning

Generate text

What teams actually run

Automated Content Generation

Semantic Search Implementation

Model Optimization

Conversational Bot Development

Building your own app? The connector is yours to use.

IBM watsonx Connector

Claude Desktop

AI Engineers

Data Scientists

Software Developers

How do I connect this MCP to my AI client?

Do I need my own IBM watsonx account?

Can I run model tuning through my agent?

What kind of models can I access?

Is this MCP hosted by Vinkius?

watsonx Discovery AI Connector

IBM QRadar AI Connector

IBM Quantum AI Connector

NS1 (IBM NS1 Premium DNS API) AI Connector

Suggestions

X Ads (Twitter) AI Connector

Box AI Connector

Gmail AI Connector

Google Maps AI Connector