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

Q: How do I manage my data when using Voyage AI (AI Embeddings API) with Claude Desktop?

You can list all uploaded files using listfiles or download specific contents using getfilecontent. If you mess up, don't worry; the tool also provides a deletefile function.

Get high-fidelity embeddings and RAG data directly into Claude Desktop, using your local files.

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 Claude Desktop

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Embeddings from Local Files

Need to index a document sitting on your hard drive? Use `upload_file` in the desktop app. This gets the file into the system so you can generate vector embeddings using `create_embeddings`, keeping all data local. You'll get contextualized chunk embeddings with `create_contextualized_embeddings`. That means it doesn't just embed the whole document; it figures out the meaning of specific parts, which is exactly what your agent needs for accurate retrieval.

Reranking Documents in Context

When your Claude Desktop session pulls back documents, you can run `rerank`. This tool takes a query and a list of retrieved chunks, then reorders them by relevance. It’s crucial for making sure the most useful context hits your prompt first. This process works with files you've uploaded via `list_files` or downloaded content from `get_file_content`. You're not just getting data; you're optimizing how Claude uses that data in a structured way.

Batch Processing for Large Sets

If you have hundreds of files to process, don't run them one by one. Use `create_batch` and upload your file via `upload_file`. This kicks off a background job that handles the heavy lifting using `list_batches`. The server gives you `get_batch` so you can check when it’s done. It runs in the background, letting Claude Desktop continue working while the embeddings are being generated for your entire corpus.

Setup guide

Set up Voyage AI (AI Embeddings API) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Voyage AI (AI Embeddings API) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Voyage AI (AI Embeddings API) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under voyage-ai-ai-embeddings-api-mcp.

json

{
  "mcpServers": {
    "voyage-ai-ai-embeddings-api-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

You access it through the native Claude Desktop app. Because you're running it locally, your agent can reach files on your filesystem or localhost dev servers without needing a public URL.

Yes. Beyond just text, you can generate embeddings from multiple sources using `create_multimodal_embeddings`. This means your agent understands the relationship between different kinds of inputs—like an image and a caption—all within the local environment.

Since you're running this locally, your file content remains on your machine. The server uses `get_file_content` to download the raw text, but it never leaves the secure context of your desktop application.

For Claude Web at claude.ai, yes. The server must be publicly reachable so you can paste the HTTPS URL into Settings > Integrations and authenticate.

You can list all uploaded files using `list_files` or download specific contents using `get_file_content`. If you mess up, don't worry; the tool also provides a `delete_file` function.

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