How to Use the Groq MCP in Google ADK

Q: Can I use Groq models for fast routing in Google ADK?

Yes, you can use chatcompletion to handle quick classification tasks before sending complex prompts to Gemini. The LPU architecture processes these routing decisions in milliseconds. This saves you money on long-context Gemini processing.

Q: How does the embedding tool work with BigQuery?

The createembedding tool generates vector representations of your text data. You can pipe these vectors directly into BigQuery's vector search engine. This allows your agent to perform fast semantic searches across enterprise databases.

Run low-latency Groq LPU inference alongside your Google ADK enterprise agent pipelines using this 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 Google ADK

Create your Vinkius account to connect Groq to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Processing enterprise voice files in Google ADK

The `transcribe_audio` tool converts customer recordings into text before passing them to your Google ADK pipelines. You can pipe this raw text directly into BigQuery for long-term storage and analysis. Because the LPU handles files up to 25MB instantly, your Gemini models can reason over hours of meetings. This pairs Google's massive context window with Groq's fast audio translation.

Vertex-grade safety using this MCP Server

The `moderate_content` tool evaluates user inputs for safety violations before they touch your enterprise Google ADK agents. This adds a critical layer of defense before data enters your Vertex AI pipelines. If a prompt fails the safety check, the agent halts execution immediately. This protects your cloud databases from processing toxic or malicious content.

LPU-accelerated chat completions for Google ADK

The `chat_completion` tool processes Llama and Mixtral models at speeds that standard cloud GPUs cannot match. This allows your Google ADK agents to generate rapid responses during live customer interactions. You configure the toolset directly in your Python code, exposing only the specific tools your agent needs. This keeps your Google Cloud infrastructure efficient and secure.

Setup guide

Set up Groq MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Groq tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Groq_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Groq tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Initialize the McpToolset using the streamable HTTP server parameters in your Python code. Pass this toolset directly into your LlmAgent constructor. You can use either Stdio or HTTP transports depending on your Google Cloud setup.

Yes, you can use `chat_completion` to handle quick classification tasks before sending complex prompts to Gemini. The LPU architecture processes these routing decisions in milliseconds. This saves you money on long-context Gemini processing.

The framework automatically queries the server endpoint to discover tools like `structured_output` and `create_embedding`. You can restrict this list using the tool_names filter during initialization. This prevents the agent from invoking unauthorized actions.

The `create_embedding` tool generates vector representations of your text data. You can pipe these vectors directly into BigQuery's vector search engine. This allows your agent to perform fast semantic searches across enterprise databases.

Your text prompts and audio files are sent over encrypted HTTPS connections directly to the Groq API. Vinkius runs the server in an isolated V8 sandbox, meaning no data persists after the request completes. Your enterprise API keys are stored securely and never exposed to the agent.

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