How to Use the Cabify MCP in Mastra AI

Q: How do I add the Cabify MCP Server to a Mastra AI agent?

Install @mastra/mcp and instantiate the client with your Vinkius URL. You can then pull the tools using mcpClient.listTools() and spread them directly into your Mastra agent configuration.

Q: Can Mastra AI automatically retry failed Cabify bookings?

Yes. You can build a Mastra workflow around requestride that automatically retries the action if the driver dispatch times out or if API limits are temporarily reached.

Q: How do I require human approval before booking a Cabify ride in Mastra AI?

Use Mastra's requireToolApproval feature on the requestride tool. The workflow will pause and wait for an administrator to approve the trip before Cabify dispatches a driver.

Q: Can I manage saved corporate offices?

Yes. Your Mastra workflows can use addsavedlocation to register new office addresses and getsavedlocations to quickly reference coordinates for recurring executive travel.

Build automated corporate travel workflows with Mastra AI and the Cabify MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cabify MCP to Mastra AI

Create your Vinkius account to connect Cabify 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 Cabify with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Cabify corporate travel automatically

The `get_ride_history` tool pulls detailed logs of all past corporate trips, including dates, driver details, costs, and business expense categories. Mastra AI processes this list through its workflow engine to flag out-of-policy rides. You can build a workflow that automatically matches these trip logs against internal budget limits. If a ride exceeds the allowed cost, Mastra branches the workflow to alert your finance team via Slack.

Build failsafe booking systems with Mastra AI

The `request_ride` tool initiates a new ride request on Cabify using precise coordinates. Mastra AI wraps this action in a resilient workflow, automatically retrying the request with exponential backoff if there's a temporary network hiccup. You can configure human-in-the-loop approvals so that high-tier rides require an admin's green light before the agent executes the booking. If the user rejects the ride, the workflow branches to `cancel_ride` to prevent accidental charges.

Optimize travel times using this MCP Server

The `get_time_estimate` tool calculates real-time trip durations based on current traffic conditions. Mastra AI feeds this data into your scheduling workflows to automatically ping employees when they need to head to the pickup spot. By combining this with `get_price_estimate` and `get_available_products`, your agent can automatically select the most cost-effective vehicle tier that still meets the employee's schedule.

Setup guide

Set up Cabify 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 Cabify 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: "cabify-mcp-client",
  servers: {
    "cabify-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Cabify 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 Cabify. 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 Cabify 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 Cabify MCP in Mastra AI

Install `@mastra/mcp` and instantiate the client with your Vinkius URL. You can then pull the tools using `mcpClient.listTools()` and spread them directly into your Mastra agent configuration.

Yes. You can build a Mastra workflow around `request_ride` that automatically retries the action if the driver dispatch times out or if API limits are temporarily reached.

Use Mastra's `requireToolApproval` feature on the `request_ride` tool. The workflow will pause and wait for an administrator to approve the trip before Cabify dispatches a driver.

Yes. Your Mastra workflows can use `add_saved_location` to register new office addresses and `get_saved_locations` to quickly reference coordinates for recurring executive travel.

Your business ride history, location coordinates, and billing details are protected by Vinkius's ephemeral execution environment. This MCP server ensures no sensitive data is cached or stored outside your active workflow session.

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