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

Q: How do I handle large-scale embedding generation with Voyage AI (AI Embeddings API) and OpenAI Agents SDK?

You process massive datasets by first using uploadfile to stage the data. Then, your agent kicks off a job via createbatch. This keeps your primary workflow clean while the heavy lifting happens in the background.

Q: What if my embedding generation job fails midway through with Voyage AI (AI Embeddings API) and OpenAI Agents SDK?

You can monitor progress using getbatch to see exactly where things stalled. If it's corrupted, you have the option to stop it immediately by calling cancelbatch, keeping your system safe.

Q: Can I mix different types of data (text, image) for embeddings with Voyage AI (AI Embeddings API) and OpenAI Agents SDK?

Absolutely. Use the createmultimodalembeddings tool. This lets your agent generate vectors from mixed media inputs—it's designed specifically to handle that complexity.

Q: How does Voyage AI (AI Embeddings API) interact with file data using OpenAI Agents SDK?

The agent first uses listfiles to see what documents are available. Then, if it needs the actual content for processing, it calls getfilecontent. This makes sure the context is always fresh and accessible.

Run complex RAG pipelines safely with OpenAI Agents 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 OpenAI Agents SDK

Create your Vinkius account to connect Voyage AI (AI Embeddings API) to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Embeddings into Your Agent Workflow

You can use `create_embeddings` to generate standard vector representations for any given text chunk. This process turns raw data into machine-readable formats, which your agent uses to find relevant context. Later, you'll call the `rerank` tool when a user query comes in. This lets you refine search results against the original documents, making sure the retrieved context is highly accurate for the final output.

Manage Large Document Batches

Instead of calling tools one by one, you'll use `upload_file` to prepare large amounts of data for batch processing. This lets your agent generate high-quality embeddings across thousands of documents at once. The system gives you a job ID that you track using `get_batch`. Once the work is done, you can check the status with `get_batch` or cancel it early by calling `cancel_batch`.

Handle Mixed Media Context

The tool `create_multimodal_embeddings` lets your agent process more than just text. You can feed it images alongside captions to generate comprehensive embeddings. If you need to deal with file metadata, start by calling `list_files`. This shows the structure of all stored assets before you decide which specific file content to download using `get_file_content`.

Setup guide

Set up Voyage AI (AI Embeddings API) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Voyage AI (AI Embeddings API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Voyage AI (AI Embeddings API) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Voyage AI (AI Embeddings API) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Voyage AI (AI Embeddings API) Agent",
            instructions="You have access to Voyage AI (AI Embeddings API) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You process massive datasets by first using `upload_file` to stage the data. Then, your agent kicks off a job via `create_batch`. This keeps your primary workflow clean while the heavy lifting happens in the background.

You can monitor progress using `get_batch` to see exactly where things stalled. If it's corrupted, you have the option to stop it immediately by calling `cancel_batch`, keeping your system safe.

Absolutely. Use the `create_multimodal_embeddings` tool. This lets your agent generate vectors from mixed media inputs—it's designed specifically to handle that complexity.

The agent first uses `list_files` to see what documents are available. Then, if it needs the actual content for processing, it calls `get_file_content`. This makes sure the context is always fresh and accessible.

The server primarily handles raw text, file metadata, and computed vector embeddings. Always confirm that the data you're sending to `create_embeddings` meets your compliance needs.

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