2,500+ MCP servers ready to use
Vinkius

Cabify MCP Server for Mastra AI 9 tools — connect in under 2 minutes

Built by Vinkius GDPR 9 Tools SDK

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Cabify through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.

Vinkius supports streamable HTTP and SSE.

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

async function main() {
  // Your Vinkius token. get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "cabify": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "Cabify Agent",
    instructions:
      "You help users interact with Cabify " +
      "using 9 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with Cabify?"
  );
  console.log(result.text);
}

main();
Cabify
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Cabify MCP Server

What you can do

Connect AI agents to the Cabify Business platform for enterprise mobility management:

Mastra's agent abstraction provides a clean separation between LLM logic and Cabify tool infrastructure. Connect 9 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.

  • Get price estimates across all Cabify tiers (Lite, Executive, Taxi)
  • Compare trip durations with real-time traffic data
  • Request rides directly with pickup and dropoff coordinates
  • Track active rides with driver info, vehicle details, and live ETA
  • Cancel rides when plans change
  • View complete ride history with business expense tracking
  • Manage saved locations for frequent business destinations
  • Check available service tiers at any location in Spain and LATAM

The Cabify MCP Server exposes 9 tools through the Vinkius. Connect it to Mastra AI 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 Cabify to Mastra AI via MCP

Follow these steps to integrate the Cabify MCP Server with Mastra AI.

01

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai

02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

03

Run the agent

Save to agent.ts and run with npx tsx agent.ts

04

Explore tools

Mastra discovers 9 tools from Cabify via MCP

Why Use Mastra AI with the Cabify MCP Server

Mastra AI provides unique advantages when paired with Cabify through the Model Context Protocol.

01

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Cabify without touching business code

02

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

03

TypeScript-native: full type inference for every Cabify tool response with IDE autocomplete and compile-time checks

04

One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure

Cabify + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the Cabify MCP Server delivers measurable value.

01

Automated workflows: build multi-step agents that query Cabify, process results, and trigger downstream actions in a typed pipeline

02

SaaS integrations: embed Cabify as a first-class tool in your product's AI features with Mastra's clean agent API

03

Background jobs: schedule Mastra agents to query Cabify on a cron and store results in your database automatically

04

Multi-agent systems: create specialist agents that collaborate using Cabify tools alongside other MCP servers

Cabify MCP Tools for Mastra AI (9)

These 9 tools become available when you connect Cabify to Mastra AI via MCP:

01

add_saved_location

Common use cases: save office addresses, frequent client locations, hotels, airports. Returns the saved location details including the new location ID. Use this to build a library of frequently used destinations for faster ride booking. Save a new location for the Cabify account

02

cancel_ride

Cancellation policies vary based on ride status - cancellations after driver assignment may incur fees depending on Cabify Empresas policy. Use this to cancel rides that were booked by mistake or are no longer needed. Cancel an existing Cabify ride request

03

get_available_products

Returns product IDs, names, descriptions, capacity, and features. Use this to see which service options are available before requesting estimates or booking rides. Get available Cabify service tiers at a location

04

get_price_estimate

Prices are in local currency (EUR for Spain, local currency for LATAM). Use this to compare costs across different Cabify service tiers before booking. Get price estimate for a Cabify ride between two locations

05

get_ride_details

Use this to track your active ride or review past trip details. Get details of a specific Cabify ride

06

get_ride_history

Returns ride date, status, origin/destination, product type, driver, cost, and business expense category. Use this to review past rides, calculate business expenses, or find previous trip details. Get ride history for the Cabify Business account

07

get_saved_locations

Returns location IDs, names, addresses, and coordinates. Use this to quickly reference saved locations for ride requests without typing full addresses. Common for frequent business destinations. Get saved locations for the Cabify account

08

get_time_estimate

Accounts for current traffic conditions and typical route times. Use this to plan schedules and compare route efficiency across different pickup/dropoff points. Get estimated trip duration for a Cabify ride

09

request_ride

Requires origin and destination coordinates. Optionally specify product ID (from get_available_products), pickup address, and dropoff address for clarity. Returns the ride ID, driver assignment status, and estimated pickup time. Use this to book a ride after confirming price and availability. Request a new Cabify ride

Example Prompts for Cabify in Mastra AI

Ready-to-use prompts you can give your Mastra AI agent to start working with Cabify immediately.

01

"Get me a price estimate from Madrid Airport to our office in Gran Vía for a Cabify Executive"

02

"Book a Cabify from the hotel to the conference center for 9am tomorrow"

03

"Show me all Cabify rides from last month with total business expenses"

Troubleshooting Cabify MCP Server with Mastra AI

Common issues when connecting Cabify to Mastra AI through the Vinkius, and how to resolve them.

01

createMCPClient not exported

Install: npm install @mastra/mcp

Cabify + Mastra AI FAQ

Common questions about integrating Cabify MCP Server with Mastra AI.

01

How does Mastra AI connect to MCP servers?

Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
02

Can Mastra agents use tools from multiple servers?

Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
03

Does Mastra support workflow orchestration?

Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.

Connect Cabify to Mastra AI

Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.