How to Use the Vectara MCP in Vercel AI SDK

Q: How do I check which datasets are available in Vectara with Vercel AI SDK?

You use the listcorpora tool. It gives you a full list of all indexed data sets managed by your account. This is the first step before any chat or search operation.

Q: Can I see previous chat history with Vectara and Vercel AI SDK?

Absolutely. Calling listchatsessions provides a record of all prior RAG chats that happened in the corpus. This lets you build session management directly into your user interface.

Q: What happens if I need to delete old data from Vectara using Vercel AI SDK?

The deletecorpusdocument tool handles this, but be warned: this action is irreversible. It permanently removes a document from the corpus, so always verify the keys before running it.

Q: Do I need to worry about listing documents before searching with Vectara and Vercel AI SDK?

It’s good practice. You can use listcorpusdocuments first, which shows all indexed files within a specific corpus key. Knowing the full scope helps you target your performsemanticsearch query precisely.

Stream AI responses into your UI 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 Vectara MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server: Grounded Chat Completions

Need a summarized answer with citations? You call `execute_rag_chat` and get an AI response that points back to the source material. This is perfect for showing users exactly where the data came from. When you stream this through your React or Next.js frontend, the user sees the text appearing in real-time—no clunky loading spinner needed. It keeps the whole experience feeling fast and responsive.

Manage Indexed Datasets

You'll often need to know what data you're working with. Use `list_corpora` to see every dataset in your Vectara account, or run `list_corpus_documents` against a specific corpus key to check document counts. This metadata is crucial for building user-facing products because it lets the developer validate the scope of the data before making expensive API calls. It's how you build trust into the tool.

Perform Targeted Semantic Searches

Don't just search by keywords; let the AI do the heavy lifting. Running `perform_semantic_search` against one or more corpora keys pulls out contextually relevant results, not just matching strings. This method means your agent gets highly focused information right away. You pass a query and the necessary corpus identifiers, and Vectara handles the complex vector math for you.

Setup guide

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

You use the `list_corpora` tool. It gives you a full list of all indexed data sets managed by your account. This is the first step before any chat or search operation.

Absolutely. Calling `list_chat_sessions` provides a record of all prior RAG chats that happened in the corpus. This lets you build session management directly into your user interface.

The `delete_corpus_document` tool handles this, but be warned: this action is irreversible. It permanently removes a document from the corpus, so always verify the keys before running it.

The server touches your indexed documents and metadata. When handling these corpus documents, all processing is confined within the MCP Server's secure sandbox environment.

It’s good practice. You can use `list_corpus_documents` first, which shows all indexed files within a specific corpus key. Knowing the full scope helps you target your `perform_semantic_search` query precisely.

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