How to Use the Umbrellar MCP in Mastra AI

Q: How do I ensure data integrity with Umbrellar and Mastra AI?

You use the combination of validatepolicy and syncproducts. This guarantees that before any action (like submitting a claim), both the policy ID and the underlying product record are current.

Run complex warranty workflows and conditional logic using 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 Umbrellar MCP to Mastra AI

Create your Vinkius account to connect Umbrellar 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 Umbrellar with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step Claim Processing

You can build a complex workflow for claim submission. First, the agent uses `check_product_eligibility`. If eligible, it proceeds to call `create_claim`. If not, the workflow branches and notifies an admin. This sequence handles failure gracefully. If the initial claim attempt fails due to a temporary API issue, Mastra's built-in retries will automatically re-attempt the process using the necessary tools.

Policy Validation and Registration

Need to validate a policy before proceeding? The agent uses `validate_policy` with specific IDs. If that passes, it can then use `register_product` to establish the initial warranty record. This reliable sequence ensures you don't proceed until both the policy and product are confirmed using these critical tools.

Comprehensive Data Reporting

The Mastra workflow can pull a complete picture of product history. It first gathers all available plans via `list_warranties` or specific details with `get_warranty`. Then, it collects the user's claim history using `list_claims`. This makes building reporting agents simple: gather data from multiple list/get tools in a robust, retrying sequence.

Setup guide

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

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

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

You define the workflow steps. For instance, you can set up a chain: `get_policy` -> check result -> if OK, then `create_claim`. Mastra handles the execution and failure handling for that whole sequence.

Yes. If you need to update several claims or sync many products, you can write a loop in your workflow using `update_claim` or `sync_products`. The agent handles the retry logic if one update fails.

The system touches product eligibility status, policy details, and claim records. All these core warranty components are available for multi-step processing via the MCP Server.

It's perfect for scheduled tasks. You can set up a nightly job that calls `list_policies` and then checks for any products needing manual attention using `check_product_eligibility`.

You use the combination of `validate_policy` and `sync_products`. This guarantees that before any action (like submitting a claim), both the policy ID and the underlying product record are current.

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