How to Use the IBM watsonx MCP in Vercel AI SDK

Q: How do I connect the IBM watsonx MCP Server to my Vercel AI SDK project?

Install ai and @ai-sdk/mcp first. Use createMCPClient with your HTTP endpoint URL, pull the tools via mcpClient.tools(), and pass them directly into generateText or streamText in your Vinkius MCP setup.

Get live, streaming text from the IBM watsonx MCP Server directly in your React UI with Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect IBM watsonx to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Streaming IBM watsonx Text into Vercel AI SDK UIs

The `generate_text` tool handles single-turn text generation tasks like summarization and analysis directly inside your Next.js edge functions. You pass this tool to the Vercel AI SDK's `streamText` function to bypass slow intermediate loading states. Your users see words appear on screen in real-time as the IBM foundation model produces them. This setup eliminates the need for complex loading spinners because the data flows straight from the IBM cloud to the client browser.

Interactive Multi-Turn Chat Sessions

The `generate_chat` tool runs multi-turn conversational AI applications directly inside your typescript code using the MCP client. By feeding this tool into the Vercel AI SDK `streamUI` function, you build responsive chat interfaces that handle back-and-forth user prompts. The SDK manages the message history state automatically while the tool pulls live responses from the watsonx deployment. You get a clean UI that updates with every turn of the conversation without lag.

Dynamic Model Selection and Discovery

The `list_models` tool fetches the active list of foundation models available in your IBM project. You use this inside your Vercel AI SDK configuration to let users switch between different LLM families directly in your app's settings panel. If you need specific model specs, `get_model_details` checks the capabilities of a chosen model before running a query. This prevents runtime errors by ensuring your frontend application only calls models that support your target task.

Setup guide

Set up IBM watsonx MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all IBM watsonx tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent IBM watsonx transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `ai` and `@ai-sdk/mcp` first. Use `createMCPClient` with your HTTP endpoint URL, pull the tools via `mcpClient.tools()`, and pass them directly into `generateText` or `streamText` in your Vinkius MCP setup.

Yes, the MCP client runs on lightweight HTTP transport, making it fully compatible with Vercel Edge Functions. This keeps your cold starts low and ensures fast response times.

The SDK automatically maps the JSON schemas from tools like `generate_text` or `generate_embeddings`. When the model decides to run a tool, the SDK executes the call and streams the output back to the user.

The SDK catches the connection drop immediately. You should call `mcpClient.close()` in your error-handling block to clean up the HTTP connection and notify the user interface.

Your prompt templates and model outputs remain isolated within V8 sandboxed containers on the Vinkius MCP host. No data is stored or logged on the proxy layer during transit to IBM's secure cloud endpoints.

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