Uber MCP Server for OpenAI Agents SDK 9 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Uber through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Uber Assistant",
instructions=(
"You help users interact with Uber. "
"You have access to 9 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Uber"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Uber MCP Server
What you can do
Connect your AI agents to the Uber platform for seamless ride management and trip planning:
The OpenAI Agents SDK auto-discovers all 9 tools from Uber through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Uber, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- Get available ride products (UberX, Black, Comfort) at any location
- Estimate prices across all ride types before booking
- Compare pickup times to choose the fastest option
- View complete trip history with pricing and route data
- Save and manage favorite places (Home, Work, custom locations)
- Autocomplete place searches for accurate pickup/dropoff coordinates
The Uber MCP Server exposes 9 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Uber to OpenAI Agents SDK via MCP
Follow these steps to integrate the Uber MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 9 tools from Uber
Why Use OpenAI Agents SDK with the Uber MCP Server
OpenAI Agents SDK provides unique advantages when paired with Uber through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Uber + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Uber MCP Server delivers measurable value.
Automated workflows: build agents that query Uber, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Uber, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Uber tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Uber to resolve tickets, look up records, and update statuses without human intervention
Uber MCP Tools for OpenAI Agents SDK (9)
These 9 tools become available when you connect Uber to OpenAI Agents SDK via MCP:
add_saved_place
Requires alias name, latitude, and longitude. Optionally include a full address string. The alias can be home, work, or any custom string. Returns the saved place details. Save a new place for the authenticated Uber user
get_place_autocomplete
Requires current user location to bias results. Returns place descriptions and structured address components. Use this to help users select valid pickup/dropoff locations before requesting rides. Autocomplete place predictions for Uber locations
get_price_estimate
Prices are in local currency. Use this to compare costs across different Uber ride types before booking. Get price estimate for an Uber ride between two locations
get_products
) available at the specified latitude/longitude. Returns product IDs, display names, capacity, and descriptions. Use this to see which ride options are available before requesting a ride or price estimate. Get available Uber products at a location
get_ride_estimate
More specific than price estimates as it targets one product. Use this to get exact pricing before requesting a ride. Get detailed ride estimate for a specific Uber product
get_saved_places
Returns place aliases, addresses, and coordinates. Use this to quickly reference saved locations for ride requests or price estimates without typing addresses. List saved places for the authenticated Uber user
get_time_estimate
Use this to compare how quickly different Uber services can pick you up. Lower times mean faster pickups. Get estimated pickup time for Uber at a location
get_trip_history
Returns trip date, start/end locations, product used, distance, and price. Use this to review past rides, calculate expenses, or find a previous trip details. Get trip history for the authenticated Uber user
get_user_profile
Use this to verify authentication and confirm which Uber account is connected. Get the authenticated Uber user profile
Example Prompts for Uber in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Uber immediately.
"Estimate the price for an UberX from my home to the airport at 3pm tomorrow"
"Show me my last 10 Uber trips with total spending"
"What Uber products are available at my current location and how fast can they pick me up?"
Troubleshooting Uber MCP Server with OpenAI Agents SDK
Common issues when connecting Uber to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Uber + OpenAI Agents SDK FAQ
Common questions about integrating Uber MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Uber with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Uber to OpenAI Agents SDK
Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.