How to Use the Uber MCP in Google ADK

Q: How does Google ADK handle Uber trip history retrieval?

The agent uses gettriphistory to review past rides. This gives you the date, start/end locations, distance traveled, and the price paid for that specific journey. You can use this data for expense reports.

Q: What is the best way to find available Uber products using Google ADK?

You call getproducts at a given location. It lists all the available ride types, including their IDs and descriptions. This ensures your agent knows every service offered before recommending one.

Q: How does MCP Server manage saving locations for Uber with Google ADK?

The agent saves places using addsavedplace. You supply an alias, latitude, and longitude. The system validates this data and returns the saved place details to your BigQuery workflow.

Run enterprise ride management logic with Google ADK for Uber.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Uber MCP to Google ADK

Create your Vinkius account to connect Uber 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 Uber with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Modeling Location Data with MCP Server

Your agent can pull a user's saved locations using `get_saved_places`. This returns place aliases, addresses, and coordinates. Instead of asking the user to type it out every time, your AI client simply selects from this list. This capability is crucial for building robust enterprise tools that rely on consistent location data points.

Comparing Ride Costs with MCP Server

The `get_price_estimate` tool lets the agent compare costs across different Uber ride types. You send two locations, and it returns prices in local currency for comparison. It helps your users choose the best value option. This is better than just getting a single quote because it provides context on multiple options.

Calculating Pickup Time Estimates with MCP Server

Need to know how long the wait will be? Your agent uses `get_time_estimate` to get an estimated pickup time for Uber at any location. Lower numbers mean faster service, giving the user immediate feedback. This feature is excellent for integrating into real-time status dashboards within a larger Google Cloud application.

Setup guide

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

The agent uses `get_trip_history` to review past rides. This gives you the date, start/end locations, distance traveled, and the price paid for that specific journey. You can use this data for expense reports.

Yes. For more precision than general estimates, your agent calls `get_ride_estimate`. This function targets one specific product and returns the exact price before the ride is booked.

You call `get_products` at a given location. It lists all the available ride types, including their IDs and descriptions. This ensures your agent knows every service offered before recommending one.

The agent saves places using `add_saved_place`. You supply an alias, latitude, and longitude. The system validates this data and returns the saved place details to your BigQuery workflow.

This MCP Server touches location and historical travel records via `get_trip_history` and `get_user_profile`. When building enterprise agents, you must ensure the agent only accesses necessary user profile details.

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