How to Use the IBM watsonx MCP in Claude

Q: How do I connect the IBM watsonx MCP Server to Claude Desktop?

Add the server configuration to your local claudedesktopconfig.json file. Once you restart the app, Claude Desktop reads the tool definitions and displays a hammer icon in the chat input.

Q: Can I run text generation through IBM watsonx in Claude Desktop?

Yes, you use the generatetext tool to execute single-turn tasks like summarization directly inside the desktop interface. For multi-turn conversations, Claude Desktop automatically switches to generatechat to maintain context.

Q: How does Claude Desktop handle model selection for IBM watsonx?

The client calls listmodels to fetch active model IDs from your IBM account. You can then ask Claude Desktop to analyze specific model specs using the getmodeldetails tool.

Q: Can I manage IBM watsonx projects from Claude Desktop?

Yes, the listprojects tool lets you view all active workspaces in your account. This ensures Claude Desktop targets the correct environment when saving templates via createprompt.

Run watsonx foundation models and tune prompts directly inside your local Claude Desktop app using our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM watsonx MCP to Claude Desktop

Create your Vinkius account to connect IBM watsonx to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup IBM watsonx with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run watsonx models directly in Claude Desktop

The `list_models` tool puts the entire IBM foundation model catalog inside your desktop chat interface. You don't need to jump back and forth between browser tabs to check which model families are available for your current task. When you need specific specs, the `get_model_details` tool pulls down lifecycle states and capabilities instantly. This lets Claude Desktop adapt its system prompt based on the exact parameters of the model you select.

Build and test prompts inside your workspace

Managing prompt templates gets easier when you run `list_prompts` inside this MCP Server. Your local Claude Desktop client pulls saved templates directly from your IBM cloud account without manual copy-pasting. If you need to make changes on the fly, the `create_prompt` tool saves new templates back to your project instantly. This keeps your team's prompt library updated right from your active chat session.

Kick off model tuning from your chat window

Training custom models usually requires complex CLI commands, but the `start_model_tuning` tool changes that. You point Claude Desktop to your training data URL, and the server handles the handshake with IBM's training cluster. Checking on progress is simple with the `get_tuning_status` tool. You get real-time updates on your tuning run without leaving your desktop workspace.

Setup guide

Set up IBM watsonx MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The IBM watsonx MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the IBM watsonx MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under ibm-watsonx-mcp.

json

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

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by IBM watsonx. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect IBM watsonx now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about IBM watsonx MCP in Claude Desktop

Add the server configuration to your local `claude_desktop_config.json` file. Once you restart the app, Claude Desktop reads the tool definitions and displays a hammer icon in the chat input.

Yes, you use the `generate_text` tool to execute single-turn tasks like summarization directly inside the desktop interface. For multi-turn conversations, Claude Desktop automatically switches to `generate_chat` to maintain context.

The client calls `list_models` to fetch active model IDs from your IBM account. You can then ask Claude Desktop to analyze specific model specs using the `get_model_details` tool.

Yes, the `list_projects` tool lets you view all active workspaces in your account. This ensures Claude Desktop targets the correct environment when saving templates via `create_prompt`.

Your cloud storage URLs and prompt templates are routed directly to IBM endpoints via secure V8 sandboxes. Vinkius never logs the body of your `start_model_tuning` requests or stores your active vector embeddings.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript