How to Use the Voyage AI (AI Embeddings API) MCP in Vercel AI SDK

Q: How do I manage embeddings with Voyage AI (AI Embeddings API) and Vercel AI SDK?

You call createembeddings to generate the vectors. Then, you pass those results directly into your streaming logic within the Vercel AI SDK. The MCP Server handles the heavy lifting in the background.

Q: Can Voyage AI (AI Embeddings API) handle complex file types for Vercel AI SDK?

Yes, you can use uploadfile to send files and then use tools like createmultimodalembeddings or createcontextualizedembeddings on the content. The MCP Server manages the parsing of those uploaded files.

Q: Can Voyage AI (AI Embeddings API) batch process data in Vercel AI SDK?

Absolutely. You use the createbatch tool to submit large jobs, and then you check their status using getbatch. The MCP Server handles all the asynchronous processing.

Stream AI results 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 Voyage AI (AI Embeddings API) MCP to Vercel AI SDK

Create your Vinkius account to connect Voyage AI (AI Embeddings API) 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 Voyage AI (AI Embeddings API) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Embeddings with the MCP Server

The `create_embeddings` tool generates basic text embeddings. This means you can take any chunk of data and convert it into a numerical vector, allowing your client to search against large knowledge bases. You'll use these vectors for Retrieval Augmented Generation (RAG). The results stream directly into the Vercel AI SDK UI, so users see the embedding process happening live—no loading spinners needed.

Multimodal Data Handling

Need to embed more than just text? Use `create_multimodal_embeddings` to handle images and other media types alongside your text. This is critical when building complex frontends that deal with mixed data inputs. Once the multimodal embeddings are created, you can pass them through the MCP Server for comparison or storage in a vector database.

Reranking Search Results

Finding initial results is only half the battle; ranking them correctly matters more. The `rerank` tool takes your query and a set of documents, then assigns a specific relevance score to each one. This mechanism lets you refine search output before streaming it back to the user in the Vercel AI SDK. It ensures the most relevant context gets shown first.

Setup guide

Set up Voyage AI (AI Embeddings API) 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 Voyage AI (AI Embeddings API) 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 Voyage AI (AI Embeddings API) 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 Voyage AI. 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 Voyage AI (AI Embeddings API) 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 Voyage AI (AI Embeddings API) MCP in Vercel AI SDK

You call `create_embeddings` to generate the vectors. Then, you pass those results directly into your streaming logic within the Vercel AI SDK. The MCP Server handles the heavy lifting in the background.

Yes, you can use `upload_file` to send files and then use tools like `create_multimodal_embeddings` or `create_contextualized_embeddings` on the content. The MCP Server manages the parsing of those uploaded files.

The server touches file metadata and embeddings, which are derived from user-uploaded content. You control what's uploaded via `upload_file`, keeping your data within your managed environment.

The tool results stream directly into your React or Next.js components. This means you get real-time feedback on actions like `list_batches` without waiting for a final API response.

Absolutely. You use the `create_batch` tool to submit large jobs, and then you check their status using `get_batch`. The MCP Server handles all the asynchronous processing.

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