How to Use the Uber MCP in Mastra AI

Q: How can Mastra AI use Uber MCP Server to verify a user?

First, you'll call getuserprofile to confirm which account is connected and authenticated. This ensures the subsequent steps in your workflow are executed under the right identity.

Q: What happens if an Uber price estimate fails with Mastra AI?

You can build a retry step. If getpriceestimate times out, the agent framework can automatically try again or fall back to a different pricing method without manual intervention.

Q: Can I use Uber MCP Server to list available products with Mastra AI?

Yes. Before requesting a ride, you should run getproducts at the location. This returns all available options and their capacity, letting your workflow decide which product type is actually suitable.

Q: Does Uber MCP Server handle complex trip planning with Mastra AI?

It does. Your agent can run a sequence: first getplaceautocomplete to validate the start/end points, then getrideestimate for pricing, and finally check gettimeestimate for speed.

Building reliable, multi-step Uber ride management workflows with Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Uber to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage saved locations using the Uber MCP Server

Don't let users keep typing addresses. `add_saved_place` lets your workflow save a new spot for the authenticated user, giving it an alias like 'Home' or 'Work'. It requires the name, lat, and long. This makes subsequent steps in your process much smoother. You can then use `get_saved_places` to retrieve this data when needed.

Get detailed ride pricing with the Uber MCP Server

When a user needs an estimate, you don't want a guess. Use `get_ride_estimate` because it targets one specific product and provides precise cost information before booking. This is better than general estimates for critical business logic. Your workflow can check the required product availability first using `get_products`.

Track pickup speed with the Uber MCP Server

Speed matters in ride-hailing. Use `get_time_estimate` to compare how fast different services can get to a location. Lower numbers mean faster pickups, and that's key for user satisfaction. This check should run early in your workflow to set accurate expectations for the customer.

Setup guide

Set up Uber MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Uber tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "uber-mcp-client",
  servers: {
    "uber-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Uber Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Uber tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Uber transactions"
);
console.log(result.text);

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 Mastra AI

First, you'll call `get_user_profile` to confirm which account is connected and authenticated. This ensures the subsequent steps in your workflow are executed under the right identity.

You can build a retry step. If `get_price_estimate` times out, the agent framework can automatically try again or fall back to a different pricing method without manual intervention.

Yes. Before requesting a ride, you should run `get_products` at the location. This returns all available options and their capacity, letting your workflow decide which product type is actually suitable.

It does. Your agent can run a sequence: first `get_place_autocomplete` to validate the start/end points, then `get_ride_estimate` for pricing, and finally check `get_time_estimate` for speed.

The server touches user location coordinates (latitude/longitude) when running place searches. It also accesses trip history details, including start and end locations, which are highly sensitive personal 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