How to Use the Lightspeed Restaurant MCP in Google ADK

Q: How do I configure Google ADK to talk to the Lightspeed Restaurant MCP Server?

Install the package with pip install google-adk. Then, initialize McpToolset using the StreamableHttpServerParameters with your Vinkius URL, and pass that toolset to your LlmAgent instance.

Q: Can I limit which Lightspeed Restaurant tools are exposed to Google ADK?

Yes. You can use the optional toolnames filter when setting up your McpToolset. This lets you restrict your agent to operational tools like listtables while blocking financial tools like getrevenuereport.

Q: Can I track active orders and staff performance?

Yes. Your agent can query listorders to check current order states and match them with staff lists pulled from listemployees. This helps you see which servers are handling the heaviest table loads.

Put Gemini's long context to work on your Lightspeed Restaurant data using Google ADK and our MCP Server to analyze menus and floors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lightspeed Restaurant MCP to Google ADK

Create your Vinkius account to connect Lightspeed Restaurant 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 Lightspeed Restaurant with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze menu engineering with Google ADK

This toolset uses `list_menu_items` and `list_categories` to pull your entire dish catalog directly into Gemini. Feed your entire menu history into Gemini's massive context window to identify underperforming dishes. Since Google ADK integrates with your Google Cloud setup, you can combine this POS data with external market trends. The agent processes the raw menu structure to suggest better pricing or layout adjustments directly inside your enterprise workspace.

Run deep revenue analysis on Google Cloud

This MCP Server lets your agent call `get_revenue_report` and `list_payments` to feed clean transactional data into your analysis pipelines. Stop copying sales numbers into spreadsheets. Pipe this live data straight into BigQuery for long-term storage and trend analysis. The agent handles the API calls in the background, making it easy to generate complex financial summaries without writing custom integration code.

Manage floor layouts and table status

Your agent invokes `list_floors` and `list_tables` to monitor seating trends and track dining room capacity. Get a real-time view of your dining room status during peak hours. By combining table data with active order counts from `get_business`, the agent can spot service delays before they ruin a customer's night. It gives your management team a clear, data-driven look at how efficiently your physical space is being used.

Setup guide

Set up Lightspeed Restaurant 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 Lightspeed Restaurant 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="Lightspeed Restaurant_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Lightspeed Restaurant 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 Lightspeed Restaurant. 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 Lightspeed Restaurant 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 Lightspeed Restaurant MCP in Google ADK

Install the package with `pip install google-adk`. Then, initialize `McpToolset` using the `StreamableHttpServerParameters` with your Vinkius URL, and pass that toolset to your `LlmAgent` instance.

Yes. You can use the optional `tool_names` filter when setting up your `McpToolset`. This lets you restrict your agent to operational tools like `list_tables` while blocking financial tools like `get_revenue_report`.

It takes advantage of Gemini's million-token context. Your agent can call `list_menu_items` and process thousands of dishes at once, cross-referencing them with categories from `list_categories` without running out of memory.

Yes. Your agent can query `list_orders` to check current order states and match them with staff lists pulled from `list_employees`. This helps you see which servers are handling the heaviest table loads.

All communication between Google ADK and your POS runs through secure, isolated sandboxes. Employee rosters from `list_employees` and order details from `get_order` are processed in memory and never written to persistent third-party storage.

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