Voyage AI (AI Embeddings API)

Voyage AI (AI Embeddings API) MCP Connector for Claude

A+

Generate high-quality text, multimodal, and contextualized embeddings, plus high-precision reranking for RAG workflows.

13 tools Official Updated Oct 1, 2026 Official Vinkius Partner

Connect your Voyage AI account to any AI agent to leverage state-of-the-art embedding and reranking models. Optimized for Retrieval-Augmented Generation (RAG), this server enables your agent to process complex data structures and find the most relevant information with surgical precision.

What you can do

  • Advanced Embeddings — Generate vectors for text, code, and documents using models like voyage-4 and voyage-code-3.
  • Contextualized Retrieval — Use voyage-context-3 to embed chunks while maintaining the context of the surrounding document, significantly reducing retrieval errors.
  • Multimodal Search — Vectorize interleaved text and images into a single vector space for visual search capabilities.
  • Smart Reranking — Refine search results using cross-encoders (rerank-2.5) to ensure the most relevant context is provided to your LLM.
  • Batch Operations — Manage large-scale data processing by initiating and monitoring batch inference jobs.

How it works

  1. Subscribe to this server
  2. Enter your Voyage AI API Key
  3. Start building high-performance RAG systems directly from your agent

Who is this for?

  • AI Engineers — building production-grade RAG pipelines that require better retrieval than standard embedding models.
  • Data Scientists — experimenting with multimodal search and contextualized chunking.
  • Developers — looking to integrate high-precision search into their applications without managing complex infrastructure.
embeddingsragrerankvector-searchmultimodal-ai

13 tools expose this connector's capabilities to your AI agent.

create_batch

Create a batch inference job

upload_file

Purpose must be "batch". Upload a file for batch inference

create_contextualized_embeddings

Create contextualized chunk embeddings

create_embeddings

Create text embeddings

create_multimodal_embeddings

Create multimodal embeddings

get_batch

Retrieve batch status

rerank

Rerank documents against a query

get_file

Specify the file ID to fetch its details. Retrieve file metadata

list_batches

No arguments are required for this operation. List all batches

cancel_batch

Provide the specific batch ID to terminate the process. Cancel a batch job

delete_file

Provide the file ID to permanently remove the file. Delete a file

get_file_content

Provide the file ID to access the stored data. Download file content

list_files

Do not query files that are marked as private. List all files

See how to talk to your AI agent using Voyage AI (AI Embeddings API).

Create embeddings for the text 'What are the benefits of vector search?' using the voyage-4 model.

I've generated the embeddings for your text using `voyage-4`. The output includes a high-dimensional vector ready for your vector database or similarity search.

Rerank these documents ["Doc A content...", "Doc B content..."] for the query 'AI safety' using rerank-2.5.

I've reranked the documents. Doc B scored significantly higher (0.92) than Doc A (0.45) for the query 'AI safety'. You should prioritize Doc B in your response.

Start a batch embedding job for the file 'file-987' using the embeddings endpoint.

The batch job has been initiated successfully. You can monitor its progress using the `get_batch` tool with the ID: `batch_v1_abc123`.

By using the `rerank` tool, 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.

Related Connectors