How to Use the Verba MCP in Vercel AI SDK

Q: How do I get an answer from Verba using the Vercel AI SDK?

Just call performragquery with your user's question. The results stream directly into your React component, giving a smooth, live experience.

Q: Can I add documents to Verba using the Vercel AI SDK?

Yep. Use addknowledgedocument. You pass both the document content and any optional metadata JSON you want stored with it in the Verba knowledge base.

Q: How do I check what documents are already in Verba with the Vercel AI SDK?

Call listknowledgedocuments. It returns a list of every document indexed in the Verba knowledge base so you can display it to your user.

Streamline your app's knowledge retrieval with the 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 Verba MCP to Vercel AI SDK

Create your Vinkius account to connect Verba 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 Verba with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Show RAG answers in real time

The `perform_rag_query` tool lets you search Verba's documents and show summarized answers instantly. Your users see the results streaming right into the UI, avoiding any loading spinners. You call this from your Next.js or Svelte frontend, passing user input to get semantic answers with citations directly within your application.

Build a document indexer

`add_knowledge_document` lets you upload new content and metadata into the Verba knowledge base. You're building product features that ingest data on the fly, making the AI smarter with every call. This tool makes it easy to track what documents are available by calling `list_knowledge_documents`, giving your frontend a real-time view of the entire index.

Manage system configuration

`get_system_config` retrieves all current settings for Verba, which is critical when building developer tools. You need to know if certain features are enabled before showing them to your users. It’s also useful to check document details using `get_document_details`. This lets you validate that a specific piece of data exists and grab its full metadata before processing it.

Setup guide

Set up Verba 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 Verba 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 Verba 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 Verba. 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 Verba 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 Verba MCP in Vercel AI SDK

Just call `perform_rag_query` with your user's question. The results stream directly into your React component, giving a smooth, live experience.

Yep. Use `add_knowledge_document`. You pass both the document content and any optional metadata JSON you want stored with it in the Verba knowledge base.

This server handles document content and associated metadata. When building your app, remember that `add_knowledge_document` is responsible for ingesting this structured information into the knowledge base.

Call `list_knowledge_documents`. It returns a list of every document indexed in the Verba knowledge base so you can display it to your user.

The server deals with structured text, specifically document content and metadata. Every operation relies on managing these types when reading or writing to the knowledge base.

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