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

Q: Can I handle large datasets with Voyage AI (AI Embeddings API) and LangChain?

Absolutely. Use the batch tools (createbatch, listbatches) to manage massive workloads without timing out your agent. The MCP Server handles the heavy lifting, freeing up your client logic for orchestration.

Q: What data types does Voyage AI (AI Embeddings API) handle when connected to LangChain?

It processes several formats: raw text using createembeddings, chunks with context via createcontextualizedembeddings, and even multimodal inputs. The output is always a structured embedding vector ready for chaining.

Build complex reasoning chains with LangChain 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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Inference Jobs with the MCP Server

You initiate long-running, high-volume tasks using `create_batch` and then monitor their status with `list_batches`. This keeps your main agent logic fast while large data sets process in the background. You'll use `get_batch` to poll for job completion or `cancel_batch` if you need to stop a runaway process early.

Contextualize Embeddings for LangChain

Don't just get basic text embeddings; `create_contextualized_embeddings` processes chunks of data while retaining semantic meaning. This is crucial when your agent needs to understand subtle context, like differentiating between two similar concepts in a document. Your AI client uses the output of this tool directly as an input variable for subsequent steps in the chain.

Advanced Document Retrieval with MCP Server

`rerank` lets your agent score documents against a query to pull out the most relevant snippets. This goes beyond simple similarity search, giving you high-precision results needed for reliable RAG steps. You first `upload_file` and then use this tool to narrow down what your chain needs to read next.

Setup guide

Set up Voyage AI (AI Embeddings API) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Voyage AI (AI Embeddings API) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "voyage-ai-ai-embeddings-api-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Voyage AI (AI Embeddings API) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

It provides the foundational data—embeddings and reranking scores—that allow your agent to make informed decisions. Instead of relying on simple keywords, the LLM sees semantically rich data it can process through its multi-step reasoning chains.

Absolutely. Use the batch tools (`create_batch`, `list_batches`) to manage massive workloads without timing out your agent. The MCP Server handles the heavy lifting, freeing up your client logic for orchestration.

It processes several formats: raw text using `create_embeddings`, chunks with context via `create_contextualized_embeddings`, and even multimodal inputs. The output is always a structured embedding vector ready for chaining.

The embeddings themselves are stateless outputs, but you can manage the input files and job metadata using `get_file` and `list_files`. You'll need to save the results if you want them available for a later session.

The MCP Server handles file metadata and the raw text used for generating embeddings. Remember that all input files are processed through the endpoint token, so keep track of what sensitive information you're sending.

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