How to Use the Arrivy MCP in Mastra AI

Q: How do I build a reliable job creation workflow for Arrivy with Mastra AI?

You design a Mastra workflow that chains the createcustomer and createtask tools. Mastra's engine ensures that the task is only created after the customer record is successfully made. You can also configure automatic retries on the createtask step in case of transient errors.

Q: Can a Mastra AI agent assign Arrivy tasks to the right crews?

Yes. Create a workflow where the agent first calls listtasks to find unassigned work. Then, it can use listcrews to check availability and finally call updatetask to assign the job to the appropriate crew. This entire dispatch logic can run automatically.

Q: Does Mastra AI support human approval for critical Arrivy operations?

Yes, Mastra AI has a requireToolApproval option. You can configure your agent so that before it executes a sensitive tool like updatetask or createcustomer, it pauses and waits for a human to approve the action. This keeps you in control of important changes.

Q: What happens if my agent tries to update an Arrivy task that no longer exists?

The Arrivy MCP tool updatetask will return an error. You can configure your Mastra AI workflow to catch this specific error and execute a different branch of logic, like logging the issue or notifying an administrator, instead of just failing.

Build bulletproof Arrivy workflows with Mastra AI. Automate your booking and dispatch operations with logic that handles errors and retries automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arrivy MCP to Mastra AI

Create your Vinkius account to connect Arrivy 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 Arrivy with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Construct multi-step booking workflows

Mastra AI lets you chain Arrivy tools into a reliable sequence. You can build a workflow that first uses `list_customers` to check if a customer exists. Based on the result, it can either `create_customer` for a new one or proceed directly to `create_task` for an existing one. This conditional logic is native to Mastra. It turns simple tools into a smart process. You define the steps, and Mastra's engine executes them, handling the flow from one action to the next without you writing complex state management code.

Automate dispatch with built-in retries

Design a dispatch agent that just works. Your workflow can fetch open jobs with `list_tasks`, find available staff with `list_crews`, and then assign the job with `update_task`. Mastra's real strength is what happens if a step fails. If the `update_task` call fails due to a network blip or a temporary lock, Mastra AI can automatically retry with exponential backoff. You don't have to code the retry loop; you just configure it. This makes your automated dispatch process far more resilient.

Deploy your Arrivy MCP Server agent anywhere

Your Mastra AI agent, configured with the Arrivy MCP Server tools, is ready for deployment. You can run it as a standalone service that monitors for new tasks or trigger it from an external event. The setup is clean and points to your single Vinkius endpoint. Use `get_account_check` as a health check in your deployed agent to ensure it's always connected to Arrivy. This setup gives you a production-ready automation engine for your field service operations, backed by a managed MCP connection.

Setup guide

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

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

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

You design a Mastra workflow that chains the `create_customer` and `create_task` tools. Mastra's engine ensures that the task is only created after the customer record is successfully made. You can also configure automatic retries on the `create_task` step in case of transient errors.

Yes. Create a workflow where the agent first calls `list_tasks` to find unassigned work. Then, it can use `list_crews` to check availability and finally call `update_task` to assign the job to the appropriate crew. This entire dispatch logic can run automatically.

Yes, Mastra AI has a `requireToolApproval` option. You can configure your agent so that before it executes a sensitive tool like `update_task` or `create_customer`, it pauses and waits for a human to approve the action. This keeps you in control of important changes.

The Arrivy MCP tool `update_task` will return an error. You can configure your Mastra AI workflow to catch this specific error and execute a different branch of logic, like logging the issue or notifying an administrator, instead of just failing.

Your data is processed securely. The connection between your Mastra agent and the MCP Server is encrypted. Vinkius operates on a zero-trust model, where every request is authenticated via your private token. The server processes your Arrivy data—like customer info and task details—only to execute the tool call.

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