How to Use the Kavak MCP in Mastra AI

Q: How do I register the Kavak MCP with Mastra AI?

Install @mastra/mcp and instantiate a new MCPClient with your endpoint URL. Call listTools() and spread the results into your agent's tool array. It automatically detects if you need SSE or Streamable HTTP.

Q: Can Mastra AI handle failed Kavak reservations?

Yes. If a call to createreservation times out, your workflow engine automatically retries the request using exponential backoff. You never lose a buyer due to a temporary network blip.

Q: Does Mastra AI support human approval for Kavak test drives?

You can wrap the scheduletestdrive tool with Mastra's requireToolApproval flag. The system pauses the workflow, pings an admin for confirmation, and only books the appointment once approved.

Q: How do I check active holds in a workflow?

Drop the listreservations tool into a scheduled cron job step. The agent polls the endpoint and alerts your team if any holds are about to expire.

Build resilient car buying workflows and automated valuation pipelines with Mastra AI and the Kavak marketplace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kavak MCP to Mastra AI

Create your Vinkius account to connect Kavak 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 Kavak with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate trade-in pricing with Mastra AI

The `estimate_trade_in` tool feeds your workflow the current Mexican market value for a user's existing car. You pass the make, model, year, and mileage into the step, and the agent calculates a baseline offer. If the initial query fails due to a missing parameter, Mastra's built-in exponential backoff catches the error and retries the request. You can then route the output into `get_market_pricing` to compare the trade-in offer against retail benchmarks.

Conditional search and finance routing

Your agent uses `search_vehicles` to find cars that fit the buyer's criteria, pulling from live inventory. You set up a branch in your workflow: if the car is over a certain price, the system automatically triggers `get_financing_options`. This means the buyer gets a complete package—the car details via `get_vehicle` and the exact monthly payment breakdown—in one response. The MCP Server handles the complex data fetching while your logic dictates the flow.

Bulletproof vehicle hold execution

Calling the MCP `create_reservation` tool demands accurate contact data because it physically removes a car from the Kavak lot. Your workflow gathers the buyer's details, requests human-in-the-loop approval, and executes the hold. If the reservation succeeds, the next step fires `schedule_test_drive` to arrange a home delivery. Should the chosen time slot fail, your logic simply loops back and asks the user for an alternative date using `list_locations` to find nearby hubs.

Setup guide

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

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

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

Install `@mastra/mcp` and instantiate a new `MCPClient` with your endpoint URL. Call `listTools()` and spread the results into your agent's tool array. It automatically detects if you need SSE or Streamable HTTP.

Yes. If a call to `create_reservation` times out, your workflow engine automatically retries the request using exponential backoff. You never lose a buyer due to a temporary network blip.

You can wrap the `schedule_test_drive` tool with Mastra's `requireToolApproval` flag. The system pauses the workflow, pings an admin for confirmation, and only books the appointment once approved.

Drop the `list_reservations` tool into a scheduled cron job step. The agent polls the endpoint and alerts your team if any holds are about to expire.

The MCP architecture processes loan parameters and vehicle IDs inside a zero-trust environment. Vinkius destroys the sandbox the second the calculation finishes, ensuring no financial queries linger in any logs.

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