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

Q: Can Voyage AI (AI Embeddings API) generate multimodal data for Mastra AI?

Yes, createmultimodalembeddings handles images and other media types. You can build a workflow where failure to process an image triggers a notification via your agent framework.

Q: How do I monitor large jobs in Mastra AI using the MCP Server?

You use listbatches to see everything submitted, and then getbatch for real-time status updates. The whole process is managed by the Voyage AI (AI Embeddings API) through the MCP Server.

Q: Does Voyage AI (AI Embeddings API) support file deletion in Mastra AI?

Yes, you can use deletefile to clean up resources after a workflow completes. This is important for managing costs and keeping your data models clean.

Build reliable, multi-step workflows with Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Voyage AI (AI Embeddings API) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Creating Contextual Embeddings for Mastra AI

The `create_contextualized_embeddings` tool builds embeddings that understand the surrounding text. When you run this, you're not just getting raw vectors; you're generating highly specific context representations. This is perfect for complex business logic in Mastra AI workflows because it means your agent can reason about data based on its *location* within a document, not just keyword matching.

Managing Batch Inference Jobs

When you need to process thousands of documents, use `create_batch` and then monitor progress with `get_batch`. The MCP Server handles the queuing and processing across multiple steps. If something goes wrong, Mastra AI can be configured to automatically retry using these batch tools, ensuring your complex workflows don't fail on a single network hiccup.

Advanced Data Reranking for Mastra AI

You can use the `rerank` tool to take multiple sources of data and score them against a given query. It gives you a precise measure of relevance, not just presence. This capability lets your Mastra AI agent perform highly targeted searches—like filtering through thousands of support tickets to find the single best answer.

Setup guide

Set up Voyage AI (AI Embeddings API) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Voyage AI (AI Embeddings API) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "voyage-ai-ai-embeddings-api-mcp-client",
  servers: {
    "voyage-ai-ai-embeddings-api-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Voyage AI (AI Embeddings API) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Voyage AI (AI Embeddings API) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Voyage AI (AI Embeddings API) transactions"
);
console.log(result.text);

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 Mastra AI

If a step fails, your Mastra AI workflow can automatically call tools like `list_batches` or re-run the embedding creation using the MCP Server. It treats the tool result itself as part of the retry logic.

This server touches file metadata, text embeddings, and batch job status. Since Mastra AI handles complex processes, you'll need to ensure your sensitive files are properly processed before they hit the MCP Server.

Yes, `create_multimodal_embeddings` handles images and other media types. You can build a workflow where failure to process an image triggers a notification via your agent framework.

You use `list_batches` to see everything submitted, and then `get_batch` for real-time status updates. The whole process is managed by the Voyage AI (AI Embeddings API) through the MCP Server.

Yes, you can use `delete_file` to clean up resources after a workflow completes. This is important for managing costs and keeping your data models clean.

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