How to Use the Lyft MCP in Google ADK

Q: How does the Google ADK process Lyft location data?

Your agent calls getlocations to retrieve your saved addresses. The Google ADK parses these coordinates and feeds them directly to Gemini, allowing the model to make intelligent decisions when planning your next trip.

Run enterprise-grade travel coordination pipelines by connecting Lyft tools to the Google ADK and Gemini ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lyft MCP to Google ADK

Create your Vinkius account to connect Lyft 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 Lyft with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Analytics Meets Lyft Travel History

Connect your corporate travel logs to your analytical databases by feeding your `get_ride_history` data directly into BigQuery. By combining the Google ADK with this MCP Server, your agent can pull historical trip data and run massive SQL queries on your actual transportation spending. You can quickly cross-reference historical data with active `get_cost_estimate` runs to find out if your team is booking rides during peak surge pricing.

Long-Context Ride Coordination with Google ADK

Gemini's million-token context window lets you feed entire travel itineraries into your agent, allowing it to lookup saved destinations via `get_locations` and automatically queue up the next ride. The Google ADK uses this massive memory to analyze your schedule. Your agent monitors active trips using `get_ride_details` without losing track of your daily agenda. If a flight is delayed, the agent calculates the new arrival time, checks `get_eta_estimate`, and updates your pickup spot.

Granular Lyft MCP Server Filtering for Enterprise Safety

Enterprise deployments require tight control over what an agent can execute, especially when checking ride availability using `get_ride_types`. The Google ADK allows you to define strict tool filters, ensuring your agent can check ride availability but cannot actually spend money. If booking is authorized, you can restrict `request_ride` to pre-approved corporate coordinates configured through `set_location`. Any attempt to book a ride outside of these parameters will be blocked by the ADK wrapper before hitting the API.

Setup guide

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

Vinkius manages the OAuth flow and provides a single secure endpoint token. You pass this token when initializing the `McpToolset` in your Google ADK configuration, granting your agent instant access to tools like `get_ride_history`.

Yes, you should build retry logic into your agent's execution loop. When polling `get_eta_estimate` frequently during peak hours, configure the Google ADK to back off gracefully if the API returns a rate limit error.

Your agent calls `get_locations` to retrieve your saved addresses. The Google ADK parses these coordinates and feeds them directly to Gemini, allowing the model to make intelligent decisions when planning your next trip.

Yes, if you wire your calendar to your agent. When an event is removed, the agent calls `cancel_ride` to terminate the active booking and prevent unnecessary cancellation charges.

All transit data, including coordinates and cost estimates, is processed in memory. Vinkius runs this MCP Server inside a secure, zero-trust, ephemeral sandbox, ensuring your destination details remain entirely confidential.

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