How to integrate Repairshopr MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Repairshopr logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Repairshopr to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Repairshopr agent that can list all upcoming appointments for today, fetch all assets linked to a customer, show attachments for a specific service case through natural language commands.

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

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

Also integrate Repairshopr with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Repairshopr integration
  • Using Composio's Tool Router to dynamically load and access Repairshopr 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 Repairshopr MCP server, and what's possible with it?

The Repairshopr MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Repairshopr account. It provides structured and secure access to your repair shop management system, so your agent can perform actions like managing customer records, handling appointments, viewing assets, retrieving attachments, and organizing contacts on your behalf.

  • Effortless appointment management: Instantly retrieve details of specific appointments, get upcoming schedules, or delete canceled slots directly through your agent.
  • Comprehensive customer and contact handling: Let your agent fetch lists of customers or contacts, update records, or permanently remove outdated customer information for streamlined CRM workflows.
  • Asset tracking and lookup: Quickly search for assets, confirm asset details, or filter assets by customer or status, making it easy to keep tabs on all equipment under management.
  • Service case and attachment retrieval: Have your agent pull all attachments linked to a specific service case, ensuring quick access to important files and documentation.
  • Estimate and invoice cleanup: Empower your agent to delete estimates or invoices that are no longer needed, helping you maintain a tidy, organized business record system.

Supported Tools & Triggers

Tools
Add Estimate Line ItemTool to add a line item to an existing estimate.
Add Purchase Order Line ItemTool to add a product line item to an existing purchase order.
Add Schedule Line ItemTool to add a line item to an invoice schedule.
Add Ticket CommentTool to add a comment to an existing ticket in RepairShopr.
Add Ticket Line ItemTool to add a line item to an existing ticket in RepairShopr.
Charge Ticket TimerTool to charge a timer entry for a specific ticket.
Convert Estimate to InvoiceTool to convert an existing estimate to an invoice in RepairShopr.
Create Appointment TypeTool to create a new appointment type in RepairShopr.
Create Canned ResponseTool to create a new Canned Response.
Create ContactTool to create a new contact associated with a customer.
Create ContractTool to create a new contract for a customer.
Create Invoice Line ItemTool to create a new line item on an existing invoice in RepairShopr.
Create PhoneTool to create a phone number for a customer.
Create Portal UserTool to create a portal user in RepairShopr.
Create Product SerialTool to create a product serial for a specific product.
Create RMM AlertTool to create an RMM Alert.
Create Invoice ScheduleTool to create a recurring invoice schedule.
Create TicketTool to create a new ticket in RepairShopr.
Create Ticket TimerTool to create a ticket timer entry for a specific ticket in RepairShopr.
Create VendorTool to create a new vendor.
Create Wiki PageTool to create a Wiki Page in RepairShopr.
Delete AppointmentTool to delete a specific appointment by its ID.
Delete Appointment TypeTool to delete an Appointment Type by ID.
Delete Canned ResponseTool to delete a specific canned response by ID.
Delete ContactTool to delete a specific contact by ID.
Delete ContractTool to delete a contract by its unique ID.
Delete CustomerTool to delete a specific customer by ID.
Delete EstimatePermanently deletes an estimate from RepairShopr by its unique ID.
Delete Estimate Line ItemTool to delete a line item from an estimate in RepairShopr.
Delete InvoiceTool to delete a specific invoice by ID.
Delete Invoice Line ItemTool to delete a specific line item from an invoice by invoice ID and line item ID.
Delete PhoneTool to delete a specific phone by ID for a given customer.
Delete Portal UserTool to permanently delete a portal user by ID.
Delete RMM AlertTool to delete/clear an RMM alert by its ID.
Delete ScheduleTool to delete a specific schedule by its ID.
Delete TicketTool to delete a specific ticket by its ID.
Delete Ticket TimerTool to delete a specific ticket timer entry by its ID.
Delete Wiki PageTool to delete a Wiki Page by its ID.
Email EstimateTool to send an estimate to a customer via email.
Email InvoiceTool to send an invoice to a customer via email.
Get AppointmentTool to retrieve details of a specific appointment by its ID.
Get AppointmentsRetrieves a list of appointments from RepairShopr.
Get Appointment TypeTool to retrieve details of a specific appointment type by ID.
Get AssetTool to retrieve details of a specific asset by its ID.
Get AssetsTool to retrieve a paginated list of assets.
Get Caller IDTool to retrieve caller identification information based on a phone number.
Get Canned Response SettingsTool to retrieve settings for Canned Responses.
Get ContactTool to retrieve a specific contact by ID.
Get ContactsTool to retrieve a paginated list of contacts.
Get ContractTool to retrieve details of a specific contract by ID.
Get CustomerTool to retrieve details of a specific customer by ID.
Get Customer Payment ProfilesTool to retrieve a paginated list of payment profiles for a specific customer.
Get CustomersTool to retrieve a list of customers.
Get Customers AutocompleteTool to retrieve a list of customers for autocomplete query.
Get Employee Time ClockTool to retrieve the last time clock entry for a specific user.
Get EstimateTool to retrieve details of a specific estimate by ID.
Get EstimatesRetrieves a paginated list of estimates from RepairShopr.
Get InvoiceTool to retrieve details of a specific invoice by ID.
Get InvoicesTool to retrieve a paginated list of invoices.
Get Invoice TicketTool to retrieve the associated ticket for a specific invoice.
Get Latest CustomerTool to retrieve the most recently created customer.
Get LeadTool to retrieve details of a specific lead by its ID.
Get LeadsTool to retrieve a paginated list of leads.
Get Current UserTool to retrieve information about the currently authenticated user.
Get PaymentTool to retrieve details of a specific payment by ID.
Get PaymentsTool to retrieve a paginated list of payments.
Get ProductRetrieves comprehensive details for a specific product by its unique ID.
Get Product by BarcodeRetrieves product details by searching for a specific barcode (UPC code).
Get ProductsRetrieve a list of products from RepairShopr with optional filtering, searching, and sorting.
Get Product CategoriesRetrieve all product categories from RepairShopr.
Get Product SerialsTool to retrieve all serial numbers for a specific product.
Get Purchase OrderTool to retrieve details of a specific purchase order by ID.
Get RMM AlertTool to retrieve details of an RMM Alert by its ID.
Get ScheduleTool to retrieve a specific schedule by ID.
Get SettingsTool to retrieve account settings for the RepairShopr instance.
Get Printing SettingsTool to retrieve printing settings configuration.
Get Settings TabsTool to retrieve the tabs settings configuration.
Get TicketTool to retrieve details of a specific ticket by its ID.
Get Tickets SettingsTool to retrieve tickets settings and configuration.
Get UserRetrieve detailed information about a specific user (staff/technician) by their unique ID.
Get User DeviceTool to retrieve details of a specific user device by its UUID.
Get UsersRetrieves a list of all users (staff members and technicians) in the RepairShopr system.
Get VendorTool to retrieve details of a specific vendor by ID.
Get Wiki PageTool to retrieve a Wiki Page by its ID.
List Appointment TypesTool to retrieve a paginated list of all appointment types.
List Canned ResponsesTool to retrieve a list of Canned Responses with optional search query.
List ContractsTool to retrieve a paginated list of contracts.
List ItemsTool to retrieve a paginated list of Part Orders.
List Line ItemsTool to retrieve a paginated list of Line Items from RepairShopr.
List New Ticket FormsTool to retrieve a paginated list of Ticket Forms.
List Payment MethodsTool to retrieve a paginated list of payment methods.
List PhonesTool to retrieve a paginated list of phone numbers for a specific customer.
List Portal UsersTool to retrieve a paginated list of Portal Users.
List Purchase OrdersTool to retrieve a paginated list of purchase orders.
List RMM AlertsTool to retrieve a paginated list of RMM Alerts.
List SchedulesTool to retrieve a paginated list of invoice schedules.
List Ticket CommentsTool to retrieve comments for a specific ticket by its ID.
List TicketsTool to retrieve a paginated list of tickets.
List Ticket TimersTool to retrieve a paginated list of Ticket Timers from RepairShopr.
List TimelogsTool to retrieve a paginated list of timelogs.
List VendorsTool to retrieve a paginated list of vendors.
List Wiki PagesTool to retrieve a paginated list of Wiki Pages.
List Worksheet ResultsTool to retrieve a paginated list of Worksheet Results for a specific ticket.
Mute RMM AlertTool to mute an RMM Alert by ID for a specified duration.
Create AppointmentTool to create a new appointment.
Create AssetTool to create a new asset.
Create CustomerTool to create a new customer.
Create EstimateTool to create a new estimate.
Create InvoiceCreate a new invoice for a customer in RepairShopr.
Create LeadTool to create a new lead.
Create PaymentCreate a payment record in RepairShopr.
Create ProductTool to create a new product in inventory.
Add Product PhotoTool to add photo(s) to a specific product.
Create Purchase OrderTool to create a new purchase order for a vendor.
Create User DeviceTool to create a new user device.
Print EstimateTool to queue a print job for an estimate.
Print InvoiceTool to queue a print job for an invoice in RepairShopr.
Print TicketTool to print a ticket by its ID.
Process Ticket FormTool to process a ticket form submission and create a new ticket in RepairShopr.
Receive Purchase OrderTool to mark a purchase order as received in RepairShopr.
Remove Ticket Line ItemTool to delete a line item from an existing ticket in RepairShopr.
Search AllTool to search across all RepairShopr entities including customers, contacts, assets, leads, invoices, estimates, tickets, products, purchase orders, vendors, reports, and wiki pages.
Update AppointmentTool to update an existing appointment by ID.
Update Appointment TypeTool to update an existing appointment type by ID.
Update AssetTool to update an existing asset by its ID.
Update Canned ResponseTool to update an existing Canned Response by ID.
Update ContactTool to update an existing contact.
Update ContractTool to update an existing contract by ID.
Update CustomerTool to update an existing customer by ID.
Update EstimateTool to update an existing estimate by ID.
Update Estimate Line ItemTool to update an existing line item on an estimate in RepairShopr.
Update InvoiceTool to update an existing invoice by ID.
Update Invoice Line ItemTool to update an existing line item on an invoice in RepairShopr.
Update LeadTool to update an existing lead by ID.
Update PhoneTool to update an existing phone number by ID.
Update Portal UserTool to update an existing Portal User by ID.
Update ProductTool to update an existing product by ID.
Update Product SerialTool to update an existing product serial by ID.
Update Invoice ScheduleTool to update an existing invoice schedule by ID.
Update Schedule Line ItemTool to update a line item in an invoice schedule.
Update TicketTool to update an existing ticket by ID in RepairShopr.
Update Ticket Line ItemTool to update an existing line item on a ticket in RepairShopr.
Update Ticket TimerTool to update an existing ticket timer entry in RepairShopr.
Update TimelogTool to update an existing timelog entry in RepairShopr.
Update User DeviceTool to update an existing user device by UUID.
Update VendorTool to update an existing vendor by ID.
Update Wiki PageTool to update an existing Wiki Page by ID.

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

Prerequisites

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

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.

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

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

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

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: ["repairshopr"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Repairshopr 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 Repairshopr-related tools through the MCP protocol

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 Repairshopr tools that the agent can use

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 repairshopr, 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

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 Repairshopr 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 Repairshopr 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: ["repairshopr"],
  });

  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 repairshopr, 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 Repairshopr 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.

How to build Repairshopr MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Repairshopr MCP?

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

Can I use Tool Router MCP with Vercel AI SDK v6?

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 Repairshopr tools.

Can I manage the permissions and scopes for Repairshopr while using Tool Router?

Yes, absolutely. You can configure which Repairshopr 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.

How safe is my data with Composio Tool Router?

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 Repairshopr data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.