How to Use the MongoDB Atlas Vector Search MCP in Vercel AI SDK

Q: How do I perform a search in Vercel AI SDK using MongoDB Atlas Vector Search?

Connect the server via the MCP transport and map the search tool to your agent. Your AI client will then call the tool with your vector parameters, returning results directly into your stream.

Q: Can I filter document results with MongoDB Atlas Vector Search in Vercel AI SDK?

Use the find tool to apply standard MQL filters alongside your vector queries. It allows for precise data retrieval within your existing application logic.

Stream vector similarity results directly into your Vercel AI SDK frontend and update your UI in real-time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MongoDB Atlas Vector Search MCP to Vercel AI SDK

Create your Vinkius account to connect MongoDB Atlas Vector Search 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 MongoDB Atlas Vector Search with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time vector search for Vercel AI SDK

Run your `search` operations directly from your Edge Functions. Because this MCP server streams data, your React or Svelte components reflect changes immediately without waiting for a full page refresh. Your AI client executes the search and pipes the payload straight to the user interface. It’s built for sub-50ms response times, keeping your application snappy while querying high-dimensional vector data.

Manage your Atlas collections in TypeScript

Use `list_collections` and `find` to audit your data structure from within your application code. You get full visibility into your MongoDB clusters without leaving your IDE or switching context. Type-safe interactions ensure your queries match your schema exactly. You’ll catch errors during development before they hit your production environment, saving you from runtime debugging nightmares.

Batch document handling with Vercel AI SDK

Trigger `insert` and `delete` operations through your AI agent to keep your recommendation engine current. This allows your app to update vector stores based on user feedback or new content ingestion automatically. Handling state changes this way keeps your logic centralized. Your agent manages the database lifecycle, and your SDK keeps the frontend synced with the latest document state.

Setup guide

Set up MongoDB Atlas Vector Search 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 MongoDB Atlas Vector Search 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 MongoDB Atlas Vector Search 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 MongoDB Atlas Vector Search. 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 MongoDB Atlas Vector Search 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 MongoDB Atlas Vector Search MCP in Vercel AI SDK

Connect the server via the MCP transport and map the `search` tool to your agent. Your AI client will then call the tool with your vector parameters, returning results directly into your stream.

Yes. The server is designed to work with streaming endpoints, letting you pipe database results into your UI as they arrive. This avoids long loading states.

Use the `find` tool to apply standard MQL filters alongside your vector queries. It allows for precise data retrieval within your existing application logic.

The server only touches the specific MongoDB collections you authorize. It operates within your private infrastructure, and no raw data leaves your controlled environment during queries.

Your connection strings and tokens reside in your environment variables. The server picks these up at runtime, ensuring no hardcoded keys in your source files.

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