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

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

Use the batch tools. Call uploadfile to queue your documents, then kick off the process using createbatch. This is designed for high throughput when dealing with enterprise data volumes.

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

Yes. The agent supports multimodal processing using the createmultimodalembeddings tool. This lets you build richer knowledge bases that combine visual context with written reports.

Q: How does Voyage AI (AI Embeddings API) interact with file data using Google ADK?

The agent first uses listfiles to check the available assets. If it needs the actual raw material, it calls getfilecontent. This keeps your entire workflow tethered to verifiable source material.

Build enterprise agents on Google Cloud with Google ADK and Voyage AI (AI Embeddings API).

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Embeddings for BigQuery Context

Start by generating standard vector embeddings using `create_embeddings`. Since the agent is running in a cloud environment, these vectors can be immediately pushed into BigQuery tables. When an agent needs to answer a question, it uses `rerank` on the stored documents. This high-precision step ensures the results pulled from your data source are exactly what the user needs.

Multi-modal Data Processing

The tool `create_multimodal_embeddings` lets you pass images and text together to generate a single, unified embedding. This is useful when dealing with reports that combine diagrams and written summaries. The agent can also handle the underlying data structure by using `get_file_content`, ensuring all necessary context from various sources gets processed.

High-Volume Batch Inference

For processing thousands of documents, you'll call `upload_file` to queue them for batch inference. The agent tracks the job status using `get_batch`, giving visibility into the entire pipeline. If a process needs to stop or restart, you can list all active jobs with `list_batches` and then manually intervene by calling `cancel_batch`.

Setup guide

Set up Voyage AI (AI Embeddings API) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Voyage AI (AI Embeddings API) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Voyage AI (AI Embeddings API)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Voyage AI (AI Embeddings API) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use the batch tools. Call `upload_file` to queue your documents, then kick off the process using `create_batch`. This is designed for high throughput when dealing with enterprise data volumes.

You monitor progress via the batch APIs. If something goes wrong, you can get a snapshot of the failure using `get_batch`'s status, or stop it cleanly by calling `cancel_batch`.

Yes. The agent supports multimodal processing using the `create_multimodal_embeddings` tool. This lets you build richer knowledge bases that combine visual context with written reports.

The agent first uses `list_files` to check the available assets. If it needs the actual raw material, it calls `get_file_content`. This keeps your entire workflow tethered to verifiable source material.

This server manages file metadata and the resulting vector embeddings. Always verify that the structure of the input files you are uploading is compliant with your enterprise security policies.

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