How to Use the IBM watsonx MCP in Windsurf

Q: How does Windsurf interact with IBM watsonx foundation models using this MCP Server?

Cascade uses the server to call generatetext directly from your workspace. It handles the API handshake behind the scenes so you can focus on writing code.

Q: Can I trigger IBM watsonx model tuning from Windsurf?

Yes, Cascade can call startmodeltuning using training files stored in your cloud storage. It then tracks the job status using gettuningstatus without interrupting your active coding session.

Q: How do I list my IBM watsonx projects in Windsurf?

The agent executes listprojects to grab your active workspace IDs. It then uses those IDs to scope your prompt management and text generation tasks.

Q: What models can I access with this server?

You can query any available IBM foundation model. The listmodels tool fetches the active catalog, and getmodeldetails shows you specific parameters.

Q: How is my prompt data secured when using this integration?

Your prompt templates and vector inputs sent to generateembeddings bypass third-party logging entirely. Vinkius runs the MCP Server in an isolated sandbox, routing your data securely to IBM Cloud.

Let Windsurf autonomously chain IBM watsonx model queries, tuning tasks, and prompt tests using 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 Windsurf

Create your Vinkius account to connect IBM watsonx to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate model evaluation in Windsurf

The `list_models` tool lets Cascade query available IBM foundation models directly within your workspace. By pulling details with `get_model_details`, your editor dynamically maps out what IBM offers. You don't have to manually inspect each model configuration. Windsurf sequences these checks back-to-back, letting you immediately select the correct endpoint for your generation work.

Run multi-turn chat loops autonomously

The `generate_chat` tool handles multi-turn conversational AI loops inside Windsurf. This MCP Server exposes the endpoint so Cascade can run iterative chat sessions directly in your workspace files. The agent writes the conversation logic, tests the output, and adjusts parameters on the fly. It reads your local files, feeds them to the IBM model, and updates your UI based on the response.

Manage and tune prompt templates

The `list_prompts` tool syncs your active workspace templates with your IBM Cloud projects. Stop copying and pasting prompts between the IBM console and your code. If the outputs don't match your standards, Cascade kicks off a tuning run using `start_model_tuning` and monitors progress with `get_tuning_status`. It keeps your development loop tight and fully automated.

Setup guide

Set up IBM watsonx MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my IBM watsonx payment history." If connected, Cascade will call the IBM watsonx tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade uses the server to call `generate_text` directly from your workspace. It handles the API handshake behind the scenes so you can focus on writing code.

Yes, Cascade can call `start_model_tuning` using training files stored in your cloud storage. It then tracks the job status using `get_tuning_status` without interrupting your active coding session.

The agent executes `list_projects` to grab your active workspace IDs. It then uses those IDs to scope your prompt management and text generation tasks.

You can query any available IBM foundation model. The `list_models` tool fetches the active catalog, and `get_model_details` shows you specific parameters.

Your prompt templates and vector inputs sent to `generate_embeddings` bypass third-party logging entirely. Vinkius runs the MCP Server in an isolated sandbox, routing your data securely to IBM Cloud.

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