How to Use the Uber MCP in OpenAI Agents SDK

Q: How does Uber work with OpenAI Agents SDK for trip tracking?

Your agent pulls past travel details by calling gettriphistory. This provides a full record, including the product used and total cost. You can build logic around this data to calculate expenses automatically.

Q: What happens if I need price comparison with Uber using OpenAI Agents SDK?

You use getpriceestimate to compare costs across different ride types before booking. It handles comparing prices in the local currency, giving your agent a range of options for the user.

Q: Can I verify an Uber account using OpenAI Agents SDK?

Yes. Your agent calls getuserprofile to confirm which Uber account is connected. This initial step verifies authentication and confirms the profile details before any transaction happens.

Q: How does MCP Server handle saving locations for Uber with OpenAI Agents SDK?

The agent can save places using addsavedplace. You just pass an alias (like 'Home' or 'Work'), latitude, and longitude. It returns the saved details so you never have to re-enter addresses.

Q: What data privacy considerations exist when integrating Uber with OpenAI Agents SDK?

This MCP Server touches user profile data via getuserprofile and trip history data through gettriphistory. Always ensure your agent only accesses the minimum required scope of location and personal travel records.

Build reliable ride management agents with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Uber to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Managing Trip History via MCP Server

Your agent fetches every ride detail using `get_trip_history`. This function returns the trip date, start/end locations, product used, distance, and price. You can let your AI client calculate total expenses or find specifics about a previous journey. Because this process is traceable through OpenAI's dashboard, you'll know exactly which steps your agent took to gather ride data, making debugging easy for production systems.

Automating Location Selection with MCP Server

The `get_place_autocomplete` tool lets your agent check valid pickup or dropoff spots before booking. You just need to pass the current user location so it can bias the results, giving you structured address components and descriptions. This prevents users from typing bad addresses, improving the quality of input for subsequent tools like `get_price_estimate`.

Determining Ride Availability with MCP Server

When a user needs to know what's available, your agent uses `get_products`. This tool lists all ride options (the products) at a specific latitude and longitude. The result includes product IDs, display names, capacity, and descriptions. Before trying to estimate a price or book anything, checking the full list of `get_products` ensures the user knows every choice they have.

Setup guide

Set up Uber MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Uber tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Uber tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Uber tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Uber Agent",
            instructions="You have access to Uber tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent pulls past travel details by calling `get_trip_history`. This provides a full record, including the product used and total cost. You can build logic around this data to calculate expenses automatically.

You use `get_price_estimate` to compare costs across different ride types before booking. It handles comparing prices in the local currency, giving your agent a range of options for the user.

Yes. Your agent calls `get_user_profile` to confirm which Uber account is connected. This initial step verifies authentication and confirms the profile details before any transaction happens.

The agent can save places using `add_saved_place`. You just pass an alias (like 'Home' or 'Work'), latitude, and longitude. It returns the saved details so you never have to re-enter addresses.

This MCP Server touches user profile data via `get_user_profile` and trip history data through `get_trip_history`. Always ensure your agent only accesses the minimum required scope of location and personal travel records.

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