How to Use the IBM watsonx MCP in Claude Code

Q: How does Claude Code run IBM watsonx queries using this MCP Server?

Claude Code connects to the server and runs generatetext or generatechat via standard input/output. It processes the text stream directly in your shell.

Q: Can I trigger IBM watsonx model tuning using Claude Code?

Yes, you can pass your training data location to startmodeltuning from your terminal. Claude Code will initiate the job and let you check its status.

Q: How do I list my active IBM watsonx projects in Claude Code?

Running listprojects pulls your active cloud environments. Claude Code displays them in your terminal so you can select the correct context.

Q: Can I generate text embeddings with this command-line tool?

Yes, you can use generateembeddings to convert text inputs into vector arrays. This is useful for piping data into local vector databases.

Q: How is my prompt definition data protected in this CLI setup?

The prompt definitions you create with createprompt are sent over TLS directly to IBM's secure endpoints. Vinkius runs the MCP Server in an isolated sandbox, ensuring your local terminal configuration files remain private and are never exposed.

Run IBM watsonx text generation, embeddings, and model tuning from your terminal via this 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 Code

Create your Vinkius account to connect IBM watsonx to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate terminal-based text generation

The `generate_text` tool triggers single-turn text generation tasks directly from your CLI session. Claude Code pipes your shell output straight into the IBM foundation models. This makes it simple to write bash scripts that summarize logs or generate documentation. You get fast responses without context switching to a browser.

Configure and run model tuning from the CLI

The `start_model_tuning` tool launches model training jobs directly from your terminal. This MCP Server lets you run tuning tasks with a simple terminal command. Once the job is active, you can monitor its progress by querying `get_tuning_status`. It fits perfectly into your existing terminal workflows and deployment scripts.

Inspect model configurations inside Claude Code

The `list_models` tool searches the active model catalog from your shell. Claude Code uses this and `get_model_details` to inspect available resources. You can quickly check model parameters, context limits, and lifecycle states. This ensures your terminal scripts always target the most efficient model available.

Setup guide

Set up IBM watsonx MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see ibm-watsonx-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest IBM watsonx transactions." It will automatically discover and invoke the available IBM watsonx tools.

Terminal

claude mcp add --transport http ibm-watsonx-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the IBM watsonx MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "ibm-watsonx-mcp": {
      "type": "url",
      "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 Code

Claude Code connects to the server and runs `generate_text` or `generate_chat` via standard input/output. It processes the text stream directly in your shell.

Yes, you can pass your training data location to `start_model_tuning` from your terminal. Claude Code will initiate the job and let you check its status.

Running `list_projects` pulls your active cloud environments. Claude Code displays them in your terminal so you can select the correct context.

Yes, you can use `generate_embeddings` to convert text inputs into vector arrays. This is useful for piping data into local vector databases.

The prompt definitions you create with `create_prompt` are sent over TLS directly to IBM's secure endpoints. Vinkius runs the MCP Server in an isolated sandbox, ensuring your local terminal configuration files remain private and are never exposed.

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