How to Use the watsonx Discovery MCP in Vercel AI SDK

Q: How do I use watsonx Discovery with the Vercel AI SDK?

You call mcpClient.tools() to get access to all available MCP tools, including those for watsonx Discovery. You then pass these functions directly into your streamText or generateText calls.

Q: Can I track the health of my project using watsonx Discovery and Vercel AI SDK?

Yep. Call getcomponentsettings to retrieve configuration details for any component in your watsonx Discovery project. This lets you check if everything is running smoothly before a user hits search.

Q: What data types can I query with watsonx Discovery and Vercel AI SDK?

You perform queries against specific collections using querydiscoverycontent. The tool accepts both natural language text and DQL (Discovery Query Language) for targeted searching.

Q: How do I get a list of all available data sources with watsonx Discovery and Vercel AI SDK?

Just run listdiscoverycollections. This function gives you a clean array of collection IDs, letting your client build out the necessary scope for any query.

Stream live search results directly into your React frontends using 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 watsonx Discovery MCP to Vercel AI SDK

Create your Vinkius account to connect watsonx Discovery 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 watsonx Discovery with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Querying with the MCP Server

The `query_discovery_content` tool lets you send a natural language query and a collection ID. Your AI client executes this search, and you stream the results right into your UI. Users see data appear live—no loading spinner needed for complex queries. This is perfect for building interactive dashboards where users need instant feedback on their search terms.

Managing Data Scope with MCP Server

Need to know what collections exist? Use `list_discovery_collections` to retrieve all available data sources in the project. You can then pass this list into your client-side logic. Alternatively, if you need to check contents, `list_collection_documents` pulls every document ID from a specific collection so you can build a dynamic navigation tree.

Checking Document Context with MCP Server

The `get_document_details` tool retrieves the metadata and current status of any indexed file. This means your client knows exactly what it's working with before displaying results. You can also check which NLP models are running using `list_available_enrichments`, giving your user a clear view of how their data was processed.

Setup guide

Set up watsonx Discovery 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 watsonx Discovery 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 watsonx Discovery 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 watsonx Discovery. 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 watsonx Discovery 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 watsonx Discovery MCP in Vercel AI SDK

You call `mcpClient.tools()` to get access to all available MCP tools, including those for watsonx Discovery. You then pass these functions directly into your streamText or generateText calls.

Yep. Call `get_component_settings` to retrieve configuration details for any component in your watsonx Discovery project. This lets you check if everything is running smoothly before a user hits search.

You perform queries against specific collections using `query_discovery_content`. The tool accepts both natural language text and DQL (Discovery Query Language) for targeted searching.

Just run `list_discovery_collections`. This function gives you a clean array of collection IDs, letting your client build out the necessary scope for any query.

This server primarily touches document metadata and indexed content. Specifically, it manages the retrieval of document status and component configuration settings.

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