How to Use the Atlas MCP in Mastra AI

Q: Can Mastra AI retry failed Atlas ticket creations?

The framework handles retries natively. If the createticket operation times out, the workflow engine automatically attempts the call again based on your backoff settings.

Build resilient support workflows that sync Atlas tickets and route customers automatically 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 Atlas MCP to Mastra AI

Create your Vinkius account to connect Atlas 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 Atlas with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional support routing

Basic bots break when an API call drops. Mastra AI lets you wrap this MCP Server's `get_customer` tool in a retry loop with exponential backoff so temporary network hiccups do not ruin the interaction. You build workflows that check the user tier first. If they hold a premium account, the logic branches to escalate the issue rather than just dumping them in the standard queue.

Automated ticket triaging

Human agents waste hours reading basic inquiries. Feed the `list_tickets` output into an evaluation node to classify incoming requests before anyone looks at them. Once categorized, the system calls `create_ticket` to assign the exact right tags and priorities. The workflow engine guarantees the sequence executes in the correct order every time.

Control this MCP Server with approvals

Sometimes you want eyes on a response before it goes out. Mastra's requireToolApproval flag pauses the execution right before the agent creates a new record. An admin checks the drafted payload. If it looks good, they click approve and the tool fires off the request to the Atlas backend.

Setup guide

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

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

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

Create a new MCPClient instance and pass the Vinkius URL in the servers config object. Then call listTools and spread the results into your agent's tool array.

The framework handles retries natively. If the `create_ticket` operation times out, the workflow engine automatically attempts the call again based on your backoff settings.

It auto-detects the transport layer for you. Whether you use SSE or Streamable HTTP, the client negotiates the connection to Vinkius without manual configuration.

Set up sequential nodes in your workflow definition. Have node one pull the user ID with `get_customer`, then pass that exact ID into node two for the `get_ticket` lookup.

We never store anything. The environment spins up specifically for your request, processes the sensitive help center articles and user IDs, then immediately destroys the container.

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