How to Use the Uber MCP in LangChain

Q: How does Uber work with LangChain for ride estimates?

LangChain lets you build a chain that calls getrideestimate. Instead of just getting one price, your agent can compare several products—like Comfort vs. XL—by running the estimate tool multiple times and presenting the differences to you.

Q: Can Uber use LangChain for trip history analysis?

Yep. By calling gettriphistory, your agent gets all the necessary data points (price, distance). You can then run a subsequent step in the chain to aggregate that expense data into a neat summary report.

Q: What happens with Uber and LangChain regarding saved places?

When you use getsavedplaces, your agent pulls up all locations linked to your account. This means if you're planning multiple rides, it's already got the addresses ready without you having to manually enter them.

Q: Does Uber support price comparison using LangChain?

Absolutely. You can run getpriceestimate for a rough idea, and if you need precision, your chain can follow up by calling the more specific getrideestimate once the product is selected.

Build complex ride management logic with LangChain's ReAct agents.

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 LangChain

Create your Vinkius account to connect Uber to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Trip Planning via MCP Server

Need to figure out the best way to get from point A to B? You can chain tools together. Start by calling `get_place_autocomplete` with your current location. Then, use the resulting structured address components to call `get_price_estimate`. This lets your agent reason through multiple steps before you even book the ride.

Reviewing Past Uber Trips

Checking out old expenses is simple with LangChain. Run `get_trip_history` to pull up a list of past rides, including dates, distances, and costs. You can then pass that data into another step in your chain—maybe calculating total quarterly travel spending or figuring out which product you used most often.

Saving and Managing Locations

Stop typing addresses every time. Use `add_saved_place` to save key spots like 'Work' or 'Home.' Later, your agent can call `get_saved_places`, pulling up all those aliases instantly. This makes the whole booking process faster and less error-prone for the user.

Setup guide

Set up Uber MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Uber tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "uber-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Uber transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

LangChain lets you build a chain that calls `get_ride_estimate`. Instead of just getting one price, your agent can compare several products—like Comfort vs. XL—by running the estimate tool multiple times and presenting the differences to you.

Yep. By calling `get_trip_history`, your agent gets all the necessary data points (price, distance). You can then run a subsequent step in the chain to aggregate that expense data into a neat summary report.

When you use `get_saved_places`, your agent pulls up all locations linked to your account. This means if you're planning multiple rides, it's already got the addresses ready without you having to manually enter them.

Absolutely. You can run `get_price_estimate` for a rough idea, and if you need precision, your chain can follow up by calling the more specific `get_ride_estimate` once the product is selected.

It primarily handles location data (latitude/longitude) and financial transaction records from your trip history. The server also requires basic user profile details to authenticate the agent's actions.

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