# How to integrate Remote retrieval MCP with Vercel AI SDK v6

```json
{
  "title": "How to integrate Remote retrieval MCP with Vercel AI SDK v6",
  "toolkit": "Remote retrieval",
  "toolkit_slug": "remote_retrieval",
  "framework": "Vercel AI SDK",
  "framework_slug": "ai-sdk",
  "url": "https://composio.dev/toolkits/remote_retrieval/framework/ai-sdk",
  "markdown_url": "https://composio.dev/toolkits/remote_retrieval/framework/ai-sdk.md",
  "updated_at": "2026-05-12T10:23:41.560Z"
}
```

## Introduction

This guide walks you through connecting Remote retrieval to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Remote retrieval agent that can show all pending laptop return orders, get company info for acme corp, validate your remote retrieval api key through natural language commands.
This guide will help you understand how to give your Vercel AI SDK agent real control over a Remote retrieval account through Composio's Remote retrieval MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Remote retrieval with

- [OpenAI Agents SDK](https://composio.dev/toolkits/remote_retrieval/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/remote_retrieval/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/remote_retrieval/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/remote_retrieval/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/remote_retrieval/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/remote_retrieval/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/remote_retrieval/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/remote_retrieval/framework/cli)
- [Google ADK](https://composio.dev/toolkits/remote_retrieval/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/remote_retrieval/framework/langchain)
- [Mastra AI](https://composio.dev/toolkits/remote_retrieval/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/remote_retrieval/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/remote_retrieval/framework/crew-ai)

## TL;DR

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

The Remote retrieval MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Remote retrieval account. It provides structured and secure access to your company’s equipment logistics, so your agent can perform actions like listing equipment return orders, validating API access, and fetching company details on your behalf.
- Comprehensive order tracking and listing: Ask your agent to retrieve a paginated list of all equipment return orders, with optional filters for status or date to keep tabs on ongoing returns.
- Company information retrieval: Let your agent pull detailed company information instantly, helping with audits, reporting, or support workflows.
- API key validation automation: Have your agent confirm that your API key is valid before performing sensitive actions, ensuring secure and authorized access every time.
- Status-based filtering of return orders: Easily filter and fetch orders by their current status (e.g., pending, completed) to streamline logistics reviews or escalation processes.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `REMOTE_RETRIEVAL_CREATE_ORDER` | Create Order | Tool to create IT asset retrieval orders for remote employees. Use when you need to schedule pickup of laptops, monitors, cell phones, or tablets from employees. Supports both return-to-company and recycle-with-data-destruction workflows. |
| `REMOTE_RETRIEVAL_GET_ALL_ORDERS` | Get All Orders | Tool to retrieve a paginated list of all orders. Use when you need to list orders with optional filters like status or dates. Call after authentication. |
| `REMOTE_RETRIEVAL_GET_COMPANY_DETAILS` | Get Company Details | Tool to retrieve detailed information for a company. Use after confirming a valid company_id. |
| `REMOTE_RETRIEVAL_GET_DEVICE_PRICES` | Get Device Prices | Tool to retrieve real-time pricing data for all supported devices. Use when you need current prices for Laptop, Monitor (17-23 inch), Monitor_27 (24-27 inch), Tablet, or Cell Phone. |
| `REMOTE_RETRIEVAL_GET_ORDER_DETAILS` | Get Order Details | Tool to retrieve specific order details by order ID. Use when you need detailed information about an order including employee info, company info, and shipment status (device_type, send_status, return_status). |
| `REMOTE_RETRIEVAL_LIST_PENDING_ORDERS` | List Pending Orders | Tool to retrieve list of all pending orders. Use when you need to check orders awaiting payment completion. Results are paginated up to 25 per page. |
| `REMOTE_RETRIEVAL_VALIDATE_USER` | RemoteRetrieval: Validate User | Tool to validate the provided API key. Use when you need to confirm the API key's validity. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Remote retrieval MCP server is an implementation of the Model Context Protocol that connects your AI agent to Remote retrieval. It provides structured and secure access so your agent can perform Remote retrieval operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

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

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install required dependencies

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

### 3. Set up environment variables

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
```bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
```

### 4. Import required modules and validate environment

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
```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,
});
```

### 5. Create Tool Router session and initialize MCP client

What's happening:
- We're creating a Tool Router session that gives your agent access to Remote retrieval 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 Remote retrieval-related tools through the MCP protocol
```typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["remote_retrieval"],
  });

  const mcpUrl = session.mcp.url;
```

### 6. Connect to MCP server and retrieve 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 Remote retrieval tools that the agent can use
```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();
```

### 7. Initialize conversation and CLI interface

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
```typescript
let messages: ModelMessage[] = [];

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

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

rl.prompt();
```

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

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 Remote retrieval 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
```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);
});
```

## Complete Code

```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: ["remote_retrieval"],
  });

  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 remote_retrieval, 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 Remote retrieval 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 Remote retrieval MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/remote_retrieval/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/remote_retrieval/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/remote_retrieval/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/remote_retrieval/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/remote_retrieval/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/remote_retrieval/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/remote_retrieval/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/remote_retrieval/framework/cli)
- [Google ADK](https://composio.dev/toolkits/remote_retrieval/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/remote_retrieval/framework/langchain)
- [Mastra AI](https://composio.dev/toolkits/remote_retrieval/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/remote_retrieval/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/remote_retrieval/framework/crew-ai)

## Related Toolkits

- [Ashby](https://composio.dev/toolkits/ashby) - Ashby is an applicant tracking system that handles job postings, candidate management, and hiring analytics.
- [Async interview](https://composio.dev/toolkits/async_interview) - Async interview is an on-demand video interview platform for streamlined hiring. Candidates record responses on their schedule, so employers can review anytime.
- [Bamboohr](https://composio.dev/toolkits/bamboohr) - BambooHR is a cloud-based HR management platform for small and mid-sized businesses. It streamlines employee data, HR workflows, and reporting in one easy interface.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Connecteam](https://composio.dev/toolkits/connecteam) - Connecteam is a workforce management platform for deskless teams, streamlining operations, HR, and team communication. It helps businesses save time by automating scheduling, time tracking, and staff engagement tasks.
- [Lever](https://composio.dev/toolkits/lever) - Lever is an applicant tracking system that blends sourcing, CRM, and analytics for recruiting. It helps companies scale hiring with collaborative workflows and actionable insights.
- [Recruitee](https://composio.dev/toolkits/recruitee) - Recruitee is collaborative hiring software that centralizes recruitment tasks for teams. It streamlines sourcing, interviewing, and hiring so you can fill roles faster.
- [Sap successfactors](https://composio.dev/toolkits/sap_successfactors) - Sap successfactors is a cloud-based human capital management suite for HR, payroll, recruiting, and talent management. It helps organizations centralize employee data and streamline the entire employee lifecycle.
- [Talenthr](https://composio.dev/toolkits/talenthr) - TalentHR is an intuitive, all-in-one HR tool for managing employee records, leave, and HR workflows. It streamlines HR operations so businesses can focus on people, not paperwork.
- [Workable](https://composio.dev/toolkits/workable) - Workable is an all-in-one HR software platform that streamlines hiring, employee management, and payroll. It helps teams simplify recruiting, onboarding, and staff operations in one place.
- [Workday](https://composio.dev/toolkits/workday) - Workday is a cloud-based ERP platform for HR, finance, and workforce analytics. It streamlines employee management, payroll, and business operations in a single system.
- [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable.
- [Google Calendar](https://composio.dev/toolkits/googlecalendar) - Google Calendar is a time management service for scheduling meetings, events, and reminders. It streamlines personal and team organization with integrated notifications and sharing options.
- [Google Drive](https://composio.dev/toolkits/googledrive) - Google Drive is a cloud storage platform for uploading, sharing, and collaborating on files. It's perfect for keeping your documents accessible and organized across devices.
- [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management.
- [Twitter](https://composio.dev/toolkits/twitter) - Twitter is a social media platform for sharing real-time updates, conversations, and news. Stay connected, informed, and engaged with communities worldwide.
- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Remote retrieval MCP?

With a standalone Remote retrieval MCP server, the agents and LLMs can only access a fixed set of Remote retrieval tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Remote retrieval 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 Remote retrieval tools.

### Can I manage the permissions and scopes for Remote retrieval while using Tool Router?

Yes, absolutely. You can configure which Remote retrieval 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 Remote retrieval data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)