How to Use the Together AI MCP in LangChain

Q: Can I use Together AI and LangChain for complex data tasks?

Absolutely. Your agent can combine generateembeddings with databases or other APIs. It’s built to run multi-step operations, making it ideal for sophisticated data pipelines.

Q: What if I need persistent context with Together AI and LangChain?

While the client is stateless by default, you can use client.session() to maintain a persistent context across multiple calls, ensuring your agent remembers previous steps in the chain.

Build complex, multi-step reasoning chains with LangChain and Together AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Together AI MCP to LangChain

Create your Vinkius account to connect Together AI 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 Together AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step Reasoning Pipelines

Your agent uses `chat_completion` to gather initial data from a user query. Next, it passes that output into `text_completion` to summarize the findings and prepare a final report draft. This lets you build entire reasoning workflows where one tool's result immediately becomes another tool’s input. You get full observability on latency and token usage via LangSmith tracing.

Data Contextualization with MCP Server

When your chain needs to check external data, the `generate_embeddings` tool handles it. It takes a list of strings and converts them into vector embeddings for comparison. This step grounds your agent in real-time data points. You can combine this functionality with databases or vector stores within the same LangChain graph.

Generating Visual Assets on Demand

Need a quick image for documentation? Just call `generate_image` with a detailed prompt. Your agent handles the request, and you get an asset back instantly. This capability lets your chain pull in visual components as part of its multi-step output process. It's perfect for complex reporting where media is required.

Setup guide

Set up Together AI 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 Together AI 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({
    "together-ai-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 Together AI 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 Together 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 Together AI 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 Together AI MCP in LangChain

LangSmith tracing tracks everything: what inputs were sent to each tool, how many tokens were used, and the output of every step. You'll see exactly where your chain spent its time.

Absolutely. Your agent can combine `generate_embeddings` with databases or other APIs. It’s built to run multi-step operations, making it ideal for sophisticated data pipelines.

While the client is stateless by default, you can use `client.session()` to maintain a persistent context across multiple calls, ensuring your agent remembers previous steps in the chain.

Yes, it supports aggregating tools from multiple servers. This means you can mix and match functionalities from different providers within one LangChain application.

The server primarily touches text strings (for embeddings, prompts, and messages) and model metadata (like available IDs).

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