How to Use the Flexport MCP in Mastra AI

Build resilient, self-healing logistics workflows using Mastra AI to handle Flexport purchase orders and shipments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flexport MCP to Mastra AI

Create your Vinkius account to connect Flexport 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 Flexport with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-retry failed customs document lookups with Mastra AI

Logistics APIs fail when port systems go offline or lag. Mastra AI uses its built-in workflow engine to run `get_document` and automatically retry the request with exponential backoff if a timeout occurs. If a document remains missing after three retries, the agent uses conditional routing. It halts the workflow and triggers an alert, preventing downstream systems from processing incomplete freight records.

Conditional branching for purchase order matching

Automate your procurement pipeline without losing control. This Flexport MCP Server lets Mastra AI agents compare actual cargo receipts against your original purchase orders. The agent runs `list_purchase_orders` to find the correct reference, then checks the corresponding shipment via `get_shipment`. If the quantities don't match, Mastra branches the workflow to flag the discrepancy for human review.

Self-healing freight billing workflows

Finance pipelines break when invoice amounts don't match shipping quotes. This integration allows your Mastra agent to run automated reconciliation loops using `list_commercial_invoices`. If the system detects an overcharge, the agent uses `get_invoice` to pull the itemized breakdown. It then triggers an automated dispute draft workflow, routing the details to your logistics manager for final approval.

Setup guide

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

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

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

You can configure Mastra to pause workflows when executing sensitive actions like `create_purchase_order`. The framework holds the execution state until an operator approves the draft PO, then resumes to push the data directly to Flexport.

Yes, Mastra's workflow engine is designed for this exact scenario. You can chain tools together, running `list_shipments` first to find active cargo, and then executing `list_shipment_invoices` to compile a financial report for each container.

You can deploy your Mastra agent to any cloud provider using a single command. The deployment package bundles the MCP client configuration, allowing your agent to query tools like `get_purchase_order` in production with minimal setup.

Mastra's built-in error handling catches the timeout exception immediately. You can define custom fallback paths, such as queuing the `download_document` request for a later run or sending a notification to your Slack channel.

Your shipment details and document metadata are processed in-memory within Vinkius's secure MCP Server sandbox. No logistics data retrieved via `get_shipment` or `list_documents` is stored on Vinkius servers, ensuring your supply chain records remain completely private.

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