How to integrate Shipengine MCP with Vercel AI SDK v6

This guide walks you through connecting Shipengine to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Shipengine agent that can generate shipping label for new order, track status of outgoing packages, validate customer address before shipping through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Shipengine account through Composio's Shipengine MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Shipengine logoShipengine
Api Key

ShipEngine is a shipping API that connects with multiple carriers to manage shipments, labels, and tracking. Streamline your shipping process and reduce manual effort with one unified tool.

66 Tools

Introduction

This guide walks you through connecting Shipengine to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Shipengine agent that can generate shipping label for new order, track status of outgoing packages, validate customer address before shipping through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Shipengine account through Composio's Shipengine MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Shipengine with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Shipengine integration
  • Using Composio's Tool Router to dynamically load and access Shipengine tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Shipengine MCP server, and what's possible with it?

The Shipengine MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Shipengine account. It provides structured and secure access to your shipping operations, so your agent can perform actions like generating shipping labels, tracking packages, validating addresses, and managing carrier integrations on your behalf.

  • Automated label creation and management: Instantly generate, purchase, and void shipping labels across multiple carriers, letting your agent streamline fulfillment without manual entry.
  • Real-time package tracking: Ask your agent to track shipments by carrier or tracking number to get up-to-date delivery statuses and shipment histories.
  • Address validation and correction: Have your agent validate and standardize shipment addresses to prevent delivery errors and reduce returns.
  • Carrier rate comparison: Enable your agent to fetch and compare real-time shipping rates from all connected carriers, helping you save on delivery costs.
  • Shipping manifest and batch processing: Let your agent generate manifests or process batches of shipments in a single command, making high-volume shipping fast and efficient.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["shipengine"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Shipengine tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Shipengine-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Shipengine tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to shipengine, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Shipengine tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Shipengine and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["shipengine"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to shipengine, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Shipengine agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Shipengine action and event your agent gets out of the box.

Add Tag to Shipment

Tool to add a tag to a shipment for organization and filtering.

Add to Batch

Tool to add shipments or rate IDs to an existing batch.

Cancel Shipment

Tool to cancel a shipment by ID.

Connect LTL Carrier

Tool to connect an LTL carrier account to ShipEngine.

Connect Shipsurance Account

Tool to connect a Shipsurance insurance account to ShipEngine.

Create Account Image

Tool to create a new account image in ShipEngine.

Create Package Type

Tool to create a custom package type definition in ShipEngine.

Create Tag

Tool to create a new tag in ShipEngine.

Create Tag 2

Tool to create a new tag for organizing shipments.

Create Warehouse

Tool to create a new warehouse.

Create Webhook

Tool to create a ShipEngine webhook.

Delete Account Image by ID

Tool to delete a ShipEngine account image by its ID.

Delete Batch

Tool to delete a batch by ID.

Delete Package

Tool to delete a custom package type by ID.

Delete Warehouse

Tool to delete a warehouse from your ShipEngine account.

Delete Webhook

Tool to delete a ShipEngine webhook subscription.

Disconnect Carrier

Tool to disconnect a carrier account from ShipEngine.

Disconnect Shipsurance

Tool to disconnect a Shipsurance insurance account from ShipEngine.

Download File

Tool to download a file from ShipEngine.

Get Account Image by ID

Tool to retrieve account image settings by label image ID.

Get Batch by External ID

Tool to retrieve batch details using an external batch ID.

Get Batch by ID

Tool to retrieve detailed information about a specific batch by its ID.

Get Batch Errors

Tool to retrieve errors that occurred during batch processing.

Get Bulk Rates

Tool to get shipping rates for multiple shipments in a single request.

Get Insurance Balance

Tool to retrieve the current Shipsurance insurance funds balance.

Get LTL Carrier Credential Requirements

Tool to retrieve credential requirements for connecting an LTL carrier.

Get LTL Carrier Features

Tool to retrieve features supported by an LTL carrier.

Get LTL Carrier Options

Tool to list available options/accessorials for an LTL carrier.

Get LTL Carrier Packages

Tool to list available package/handling unit types for an LTL (Less Than Truckload) carrier.

Get LTL Carrier Services

Tool to list available services for an LTL carrier.

Get Package by ID

Tool to get details of a specific custom package type by ID.

Get Shipment by External ID

Tool to retrieve shipment details using an external shipment ID.

Get Shipment by ID

Tool to retrieve a shipment by ID.

Get Shipment Rates

Tool to retrieve shipping rates for an existing shipment.

Get Tracking Information

Tool to retrieve tracking information for a shipment.

Get Warehouse by ID

Tool to retrieve details of a specific warehouse by ID.

Get Webhook by ID

Tool to retrieve details of a specific webhook by ID.

List Account Images

Tool to list all account images.

List Account Settings

Tool to list all account settings for the ShipEngine account.

List Batches (v2)

Tool to list all batches with comprehensive filtering options.

List Carrier Package Types

Tool to list all available package types for a specific carrier.

List Labels (Extended)

Tool to list all shipping labels with comprehensive filtering options.

List LTL Carriers

Tool to list all LTL (Less-Than-Truckload) carrier accounts connected to your ShipEngine account.

List Manifests (Advanced)

Tool to list all manifests with optional filtering by warehouse and carrier.

List Packages

Tool to list all package types.

List Scheduled Pickups

Tool to list all scheduled pickups with optional filters.

List Shipments (v2)

Tool to list all shipments with optional filtering parameters.

List Tags (v2)

Tool to list all tags in your account.

List Warehouses

Tool to list all warehouses.

List Webhook Events

Retrieve a list of available webhook event types supported by ShipEngine.

List Webhooks

Tool to list all webhooks configured on your account.

Parse Address

Tool to parse unstructured address text and extract structured address components.

Process Batch Labels

Tool to process a batch to create and purchase shipping labels for all shipments in the batch.

Remove From Batch

Tool to remove shipments or rate IDs from a batch.

Remove Tag from Shipment

Tool to remove a tag from a shipment.

Start Tracking Package

Tool to subscribe to tracking updates for a package via webhooks.

Stop Tracking Package

Tool to unsubscribe from tracking updates for a package.

Track LTL Shipment

Tool to track an LTL shipment using carrier code and PRO number.

Update Account Image By ID

Tool to update an account image by ID in ShipEngine.

Update LTL Connection

Tool to update LTL carrier connection credentials in ShipEngine.

Update Package Type

Tool to update an existing custom package type definition.

Update Shipment

Tool to update an existing shipment's details.

Update Shipments Tags

Tool to update tags on one or more shipments in bulk.

Update Warehouse

Tool to update an existing warehouse's details and address.

Update Webhook

Tool to update a ShipEngine webhook.

Validate Address

Tool to validate and normalize shipping addresses.

FRAMEWORKS

How to build Shipengine MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Shipengine MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Shipengine MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Shipengine MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Shipengine MCP with Claude Cowork

Codex logo

Codex

Use Shipengine MCP with Codex

OpenClaw logo

OpenClaw

Use Shipengine MCP with OpenClaw

Hermes logo

Hermes

Use Shipengine MCP with Hermes

CLI logo

CLI

Use Shipengine MCP with CLI

Google ADK logo

Google ADK

Use Shipengine MCP with Google ADK

LangChain logo

LangChain

Use Shipengine MCP with LangChain

Mastra AI logo

Mastra AI

Use Shipengine MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Shipengine MCP with LlamaIndex

CrewAI logo

CrewAI

Use Shipengine MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Shipengine MCP server, the agents and LLMs can only access a fixed set of Shipengine tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Shipengine and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Shipengine tools.

Yes, absolutely. You can configure which Shipengine scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Shipengine data and credentials are handled as safely as possible.

Start with Shipengine.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Shipengine tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies