How do I connect Voyage AI to my AI client?

You subscribe to the MCP on Vinkius and enter your Voyage AI API key. Once connected, your client can immediately use the capabilities.

What makes these embeddings better for RAG?

The MCP provides contextualized embeddings that look at surrounding text and reranking capabilities that sort results for much higher precision.

Can I process large amounts of data at once?

Yes, you can use the create_batch capability to start large-scale inference jobs and monitor them with get_batch.

Does this support images?

Yes, the create_multimodal_embeddings capability allows you to vectorize text and images into the same space.

Which clients are compatible?

This MCP works with any MCP-compatible client, including Claude, Cursor, and Windsurf.

How does reranking improve my RAG system's accuracy?

By using the rerank capability, your agent can take a list of potentially relevant documents and re-score them using a powerful cross-encoder model. This ensures that the most semantically relevant pieces of information are ranked first, providing better context for the LLM to answer queries.

What is the benefit of using contextualized embeddings?

The create_contextualized_embeddings capability allows you to embed chunks of text while considering the surrounding content of the same document. This prevents loss of meaning that often happens with standard chunking, leading to much higher retrieval precision.

Can I process images and text in the same vector space?

Yes! With create_multimodal_embeddings, you can provide interleaved sequences of text and image URLs. Voyage AI will generate a single embedding that represents the combined semantic meaning, perfect for visual or hybrid search.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Voyage AI AI Embeddings API to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get surgical precision for your RAG retrieval and search.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 13 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 13 available through Voyage AI.

01
Create batch
This capability starts a new batch inference job for large scale processing.
02
Upload file
This capability uploads a file specifically for use in batch inference tasks.
03
Create contextualized embeddings
This capability generates embeddings for text chunks while preserving the context of the surrounding document.
04
Create embeddings
This capability generates standard text embeddings for your data.

Capability set02 / 04

05-07

3 capabilities in this set.

Part of 13 available through Voyage AI.

05
Create multimodal embeddings
This capability creates embeddings that represent both text and images in a single vector space.
06
Get batch
This capability checks the current status of a specific batch job.
07
Rerank
This capability reorders a list of documents against a query to find the best matches.

Capability set03 / 04

08-10

3 capabilities in this set.

Part of 13 available through Voyage AI.

08
Get file
Use this to pull metadata for a specific file via its ID.
09
List batches
This capability returns a list of all your current and past batch jobs.
10
Cancel batch
Use this to stop a running batch job by providing its specific ID.

Capability set04 / 04

11-13

3 capabilities in this set.

Part of 13 available through Voyage AI.

11
Delete file
Use this to permanently remove a file from your storage using its file ID.
12
Get file content
Use this to download the actual data stored within a specific file ID.
13
List files
This capability lists all available files in your Voyage AI storage, excluding any marked as private.

Real work

What teams actually run

Advanced RAG Pipelines

Use reranking to ensure your agent only sees the most relevant context for a query.

Codebase Search

Generate specialized embeddings to help your agent navigate complex code repositories.

Multimodal Retrieval

Search through image and text collections simultaneously using a single vector space.

Large Scale Indexing

Run batch jobs to process entire document libraries for vectorization.

Automate a task

Put Voyage AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Voyage AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Voyage AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

959ms average. Fast in production.

Voyage AI is checked daily against the live service.

Daily averagePeak 1358ms

Oct 3Today

Fastest day: 770ms
Slowest day: 1358ms
14-day trend: Slowing+12%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 13 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Voyage AI, so you can see the experience inside your AI.

It does not authenticate your account with Voyage AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Voyage AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_x7lwFbbAdz5StvxoOu2Tkh9eDMu9Uh5i3GKObLMP/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Voyage AI capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "voyage-ai-ai-embeddings-api-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_x7lwFbbAdz5StvxoOu2Tkh9eDMu9Uh5i3GKObLMP/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Voyage AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Voyage AI owners hand off.

This MCP is built for technical users who need better retrieval than standard models provide.

01
AI Engineers
They hand off the task of building production-grade RAG pipelines to their agent.
02
Data Scientists
They use the agent to run experiments with multimodal search and chunking.
03
Developers
They use the agent to add high-precision search to apps without managing infrastructure.

FAQ

Questions Voyage AI owners ask.

01
How do I connect Voyage AI to my AI client?
You subscribe to the MCP on Vinkius and enter your Voyage AI API key. Once connected, your client can immediately use the capabilities.
02
What makes these embeddings better for RAG?
The MCP provides contextualized embeddings that look at surrounding text and reranking capabilities that sort results for much higher precision.
03
Can I process large amounts of data at once?
Yes, you can use the create_batch capability to start large-scale inference jobs and monitor them with get_batch.
04
Does this support images?
Yes, the create_multimodal_embeddings capability allows you to vectorize text and images into the same space.
05
Which clients are compatible?
This MCP works with any MCP-compatible client, including Claude, Cursor, and Windsurf.
06
How does reranking improve my RAG system's accuracy?
By using the rerank capability, your agent can take a list of potentially relevant documents and re-score them using a powerful cross-encoder model. This ensures that the most semantically relevant pieces of information are ranked first, providing better context for the LLM to answer queries.
07
What is the benefit of using contextualized embeddings?
The create_contextualized_embeddings capability allows you to embed chunks of text while considering the surrounding content of the same document. This prevents loss of meaning that often happens with standard chunking, leading to much higher retrieval precision.
08
Can I process images and text in the same vector space?
Yes! With create_multimodal_embeddings, you can provide interleaved sequences of text and image URLs. Voyage AI will generate a single embedding that represents the combined semantic meaning, perfect for visual or hybrid search.

Explore

More in Developer Tools

Connect Voyage AI to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create batch

Upload file

Create contextualized embeddings

Create embeddings

05-07

Create multimodal embeddings

Get batch

Rerank

08-10

Get file

List batches

Cancel batch

11-13

Delete file

Get file content

List files

What teams actually run

Advanced RAG Pipelines

Codebase Search

Multimodal Retrieval

Large Scale Indexing

Building your own app? The connector is yours to use.

Voyage AI Connector

Claude Desktop

AI Engineers

Data Scientists

Developers

How do I connect Voyage AI to my AI client?

What makes these embeddings better for RAG?

Can I process large amounts of data at once?

Does this support images?

Which clients are compatible?

How does reranking improve my RAG system's accuracy?

What is the benefit of using contextualized embeddings?

Can I process images and text in the same vector space?

Marqo AI (Vector Search & Embeddings) AI Connector

Typesense Vector Search AI Connector

Elasticsearch Vector AI Connector

MongoDB Atlas Vector Search AI Connector

Suggestions

Vertex AI Vector Search AI Connector

ClickHouse (Vector Search) AI Connector

Redis Vector AI Connector

Lucidworks Fusion (AI Search & Discovery) AI Connector