How to Use the Groq MCP in LangChain

Q: How do I add the Groq MCP Server to my LangChain setup?

Install langchain-mcp-adapters and langgraph via pip. Initialize MultiServerMCPClient with the server's HTTP transport URL, call client.gettools(), and pass those tools directly into your createagent call.

Q: Does the Groq integration support streaming completions inside LangChain?

This MCP Server provides synchronous tool execution for chatcompletion to ensure compatibility with standard LangChain tool-calling interfaces. For high-frequency loops, the raw throughput of the LPU still delivers responses faster than typical streaming setups on other platforms.

Q: How do I list available models within a LangChain run?

Use the listmodels tool inside your chain to query active models on the LPU platform. Your LangChain agent can call getmodel dynamically to inspect model limits before routing high-token prompts to the correct endpoint.

Run ultra-fast LPU inference directly inside your LangChain reasoning loops with this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Groq MCP to LangChain

Create your Vinkius account to connect Groq 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 Groq with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain fast LPU completions in LangChain

The `chat_completion` tool feeds Llama or Mixtral outputs directly into your LangChain prompt templates at sub-second speeds. Your agent gets raw tokens back fast enough that it doesn't stall the user's screen during complex multi-step ReAct decisions. We pass the output of this high-speed inference step directly to the next link in your run tree. LangSmith tracks every tool call, letting you monitor the exact latency drop of your LPU-accelerated runs compared to traditional cloud setups.

Enforce JSON schemas in LangChain agents

The `structured_output` tool forces Groq's engine to return strictly parsed JSON payloads that fit your LangChain Pydantic schemas. This stops your agent from breaking when it passes data to downstream databases or external APIs. If the incoming data is messy, your agent runs `moderate_content` first to check for safety violations before generating the JSON. This keeps your pipeline secure and prevents bad inputs from wasting API credits on deeper reasoning steps.

Process audio inputs inside LangChain pipelines

The `transcribe_audio` tool converts voice files to raw text directly within your LangChain document loaders. For multilingual workflows, the `translate_audio` tool translates spoken audio into English text before feeding it into your prompt chains. This MCP Server handles the audio conversion on the fly so your agent doesn't need external transcription libraries. Once the text is ready, the chain can automatically generate embeddings or kick off a chat completion step.

Setup guide

Set up Groq 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 Groq 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({
    "groq-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 Groq 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 Groq. 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 Groq 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 Groq MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize `MultiServerMCPClient` with the server's HTTP transport URL, call `client.get_tools()`, and pass those tools directly into your `create_agent` call.

Yes, when you run this server with LangChain, LangSmith automatically captures every tool execution. You can inspect the exact millisecond-level execution times for `chat_completion` and see how much faster the LPU is compared to standard GPU endpoints.

This MCP Server provides synchronous tool execution for `chat_completion` to ensure compatibility with standard LangChain tool-calling interfaces. For high-frequency loops, the raw throughput of the LPU still delivers responses faster than typical streaming setups on other platforms.

Use the `list_models` tool inside your chain to query active models on the LPU platform. Your LangChain agent can call `get_model` dynamically to inspect model limits before routing high-token prompts to the correct endpoint.

Your audio files, prompt strings, and JSON schemas pass through an ephemeral V8 sandbox directly to the Groq API. Vinkius handles the endpoint authentication token securely, ensuring no payload is cached or stored on disk during transit.

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