How to Use the IBM watsonx MCP in VS Code Copilot

Q: How does my team share the IBM watsonx MCP setup in VS Code Copilot?

You commit an .vscode/mcp.json file to your repository root. Every developer on your team gets instant access to tools like listmodels when they open the project.

Q: Can I run embedding tasks with IBM watsonx in VS Code Copilot?

Yes, the generateembeddings tool is fully accessible within the chat interface. You can pass raw text blocks to the tool and receive vector arrays directly in your VS Code Copilot workspace.

Q: How do I switch projects using IBM watsonx in VS Code Copilot?

You use the listprojects tool to view your available cloud workspaces. From there, you can instruct VS Code Copilot to target specific project IDs for your tasks.

Q: Is there a way to view model lifecycles within VS Code Copilot?

The getmodeldetails tool retrieves lifecycle states and model families from your account. This helps VS Code Copilot avoid using deprecated foundation models in your codebase.

Bring IBM watsonx foundation models and tuning pipelines into your team's VS Code Copilot workflow.

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 VS Code Copilot

Create your Vinkius account to connect IBM watsonx to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Share prompt templates across your VS Code team

The `list_prompts` tool allows VS Code Copilot to access your team's shared prompt library instantly. You don't have to share prompt files over Slack or commit raw text templates to git. When a developer needs to build a new template, they use `create_prompt` directly from the chat panel. This updates the central IBM project repository so the whole team has immediate access.

Use the IBM watsonx MCP Server for text generation

Running `generate_text` inside VS Code Copilot lets your team test single-turn generation tasks without switching to a browser. The tool returns model outputs directly into your active editor window. If your project requires complex conversational logic, the `generate_chat` tool handles multi-turn sessions. VS Code Copilot uses these responses to verify your application's dialogue flow.

Track tuning jobs directly in your editor

Launching custom training runs is straightforward with the `start_model_tuning` tool. VS Code Copilot sends the training data URL to IBM's cloud infrastructure to kick off the process. Developers can check the run's progress using the `get_tuning_status` tool. This keeps your team updated on the model's status without needing access to the cloud console.

Setup guide

Set up IBM watsonx MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the IBM watsonx MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the IBM watsonx tools listed. Try asking: "List my recent IBM watsonx transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

You commit an `.vscode/mcp.json` file to your repository root. Every developer on your team gets instant access to tools like `list_models` when they open the project.

Yes, the `generate_embeddings` tool is fully accessible within the chat interface. You can pass raw text blocks to the tool and receive vector arrays directly in your VS Code Copilot workspace.

You use the `list_projects` tool to view your available cloud workspaces. From there, you can instruct VS Code Copilot to target specific project IDs for your tasks.

The `get_model_details` tool retrieves lifecycle states and model families from your account. This helps VS Code Copilot avoid using deprecated foundation models in your codebase.

No, all requests are stateless and pass through secure, ephemeral V8 isolates. Your model parameters and prompt templates are never stored on Vinkius servers.

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