How to Use the DataStax Astra DB Vector MCP in Vercel AI SDK

Q: How do I perform a vector search with DataStax Astra DB Vector and the Vercel AI SDK?

Just call generateText or streamText and ask your AI client to use the vectorsearch tool. The Vercel AI SDK automatically handles streaming the tool's output, so you can render results directly in your React components as they arrive.

Q: Can I insert new documents into Astra DB using this server?

Yes. The insertdocument tool lets your agent add new documents to any collection. You can even include a $vector key if you're working with embeddings.

Q: Is it possible to list all collections in my DataStax Astra DB Vector namespace with the Vercel AI SDK?

Absolutely. Your agent can use the listcollections tool. This is useful for building dynamic UIs where the user can choose which collection to search or manage.

Q: What's the difference between finddocuments and vectorsearch on this MCP server?

Use vectorsearch for similarity searches based on embeddings. Use finddocuments for traditional NoSQL queries where you filter by field values, like finding all documents where status: "active".

Stream vector search results from Astra DB directly into your React UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataStax Astra DB Vector MCP to Vercel AI SDK

Create your Vinkius account to connect DataStax Astra DB Vector 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 DataStax Astra DB Vector with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Vector Search in Your UI

Use the `vector_search` tool to run similarity searches on your Astra DB collections. The Vercel AI SDK streams results as they come in, so your users see matches appearing one by one. It's a much better experience than waiting for a whole list to load. You can also combine this with `find_one_document` to fetch full details for a selected item. Since it's all streaming, the UI feels incredibly responsive. Your frontend code gets the data it needs, when it needs it.

Manage Documents without a Backend

Let your users interact with Astra DB directly from your web app. The `insert_document` and `delete_document` tools give your AI client the power to create and remove records on the user's behalf. You can build admin panels or user-facing forms that write straight to the database. It's not just about writing. Your agent can also use `list_collections` to see what's available or `count_documents` to show stats. This MCP Server gives your Vercel AI SDK app full control over your data.

Run NoSQL Queries from your Vercel AI SDK App

This isn't just for vector search. You can perform standard document lookups using `find_documents`. It's perfect for when you need to filter records based on specific fields, not just vector similarity. Your AI client can use the `find_one_document` tool to grab a single, specific record, like a user profile or a product entry. With this MCP, your agent can answer questions or populate UI components with precise data from Astra DB.

Setup guide

Set up DataStax Astra DB Vector 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 DataStax Astra DB Vector 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 DataStax Astra DB Vector 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 DataStax Astra DB. 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 DataStax Astra DB Vector 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 DataStax Astra DB Vector MCP in Vercel AI SDK

Just call `generateText` or `streamText` and ask your AI client to use the `vector_search` tool. The Vercel AI SDK automatically handles streaming the tool's output, so you can render results directly in your React components as they arrive.

Yes. The `insert_document` tool lets your agent add new documents to any collection. You can even include a `$vector` key if you're working with embeddings.

Absolutely. Your agent can use the `list_collections` tool. This is useful for building dynamic UIs where the user can choose which collection to search or manage.

Use `vector_search` for similarity searches based on embeddings. Use `find_documents` for traditional NoSQL queries where you filter by field values, like finding all documents where `status: "active"`.

Your Astra DB documents and collection data are only passed through Vinkius's ephemeral, zero-trust sandbox during tool execution. The MCP Server doesn't store your data. Your Vinkius endpoint token handles authentication, keeping your database credentials separate and secure.

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