How to integrate Quo MCP with Vercel AI SDK v6

This guide walks you through connecting Quo to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Quo agent that can get call details and voicemails, get messages, manage contacts, create tasks, and manage webhooks through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Quo account through Composio's Quo 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
Quo logoQuo
Api Key

Quo is a business phone platform for calls, SMS, contacts, and team conversations. It helps teams manage customer communication from one shared, searchable workspace.

36 Tools

Introduction

This guide walks you through connecting Quo to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Quo agent that can get call details and voicemails, get messages, manage contacts, create tasks, and manage webhooks through natural language commands.

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

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

Also integrate Quo 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 Quo integration
  • Using Composio's Tool Router to dynamically load and access Quo 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 Quo MCP server, and what's possible with it?

The Quo MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Quo account. It provides structured and secure access to your business calls, messages, contacts, conversations, tasks, users, and webhooks, so your agent can review calls, send text messages, manage contacts, organize conversations and tasks, and monitor webhook activity on your behalf.

  • Call and voicemail review: Have your agent review call participants, routing, status, timing, recordings, voicemail transcripts, and recording details.
  • Messaging and conversation management: Direct your agent to find and read messages, send texts from your Quo numbers, and mark conversations as read, open, or done.
  • Contact organization: Let the agent create, find, update, or delete contacts while working with standard details, custom fields, and external source information.
  • Task coordination: Instruct your agent to create and edit tasks, connect them to calls or conversations, assign teammates, set due dates, and complete or reopen work.
  • Webhook monitoring: Have your agent create, update, review, or remove webhook subscriptions and inspect their delivery activity and outcomes.

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: ["quo"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Quo 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 Quo-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 Quo 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 quo, 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 Quo 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 Quo 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: ["quo"],
  });

  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 quo, 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 Quo 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 Quo action and event your agent gets out of the box.

Create Contact

Create a Quo contact with standard fields, optional custom fields, and external source metadata.

Create Task

Create a task linked to exactly one phone number, conversation, or activity.

Create Webhook

Create one unified webhook subscription for selected Quo events and return its signing secret, which must be stored securely.

Delete Contact

Permanently delete one Quo contact by ID.

Delete Task

Permanently delete one Quo task by ID.

Delete Webhook

Permanently delete one unified Quo webhook and revoke its signing secret.

Get Call

Get one call and its routing, participants, status, and timing details by ID.

Get Call Voicemail

Get voicemail processing status, transcript, duration, and recording URL for a Quo call.

Get Contact

Get one contact with default and custom fields by Quo contact ID.

Get Message

Get one message by Quo message ID, including its content, related IDs, participants, delivery status, and timestamps.

Get Phone Number

Get one Quo phone number and its assignments and restrictions by ID.

Get Task

Get one task and its current links, assignee, due date, and completion state.

Get User

Get one workspace user by Quo user ID.

Get Webhook

Get one unified Quo webhook by its numeric ID.

Get Webhook Delivery

Get the payload and attempt details for one Quo webhook delivery event.

List Call Recordings

List recording segments for a Quo call in chronological order.

List Calls

List calls between a Quo number and one external participant with optional user and creation-time filters.

List Contact Custom Fields

List the workspace's contact custom-field definitions for constructing valid contact values.

List Contacts

List contacts, optionally filtered by external IDs or source, with stable-v1 phone and custom fields.

List Conversations

List inbox conversations with optional phone-number, user, creation-time, update-time, and inactive-state filters.

List Messages

List messages exchanged by a Quo phone number and one or more participants, optionally filtered by sender or creation time.

List Phone Numbers

List Quo phone numbers and their assigned users, calling restrictions, and messaging restrictions.

List Tasks

List workspace tasks with cursor-controlled pagination.

List Users

List workspace users and return one cursor-controlled page.

List Webhook Deliveries

List one page of delivery events for a unified Quo webhook, optionally filtered by status, event type, or dispatch time.

List Webhooks

List unified Quo webhooks across call, message, contact, task, and integration event families.

Send Message

Send an irreversible text message from a Quo number to one or more recipients.

Send Message and Mark Conversation Done

Send an irreversible text message from a Quo number and move the resulting inbox conversation to Done.

Set Conversation Status

Set a Quo conversation to read, done, or open.

Set Task Assignee

Assign or unassign a Quo user on a task.

Set Task Completion

Complete or reopen a Quo task.

Set Task Conversation Link

Link or unlink a Quo task and conversation.

Set Task Due Date

Set or remove a Quo task's due date.

Update Contact

Patch selected standard, custom, or source fields on an existing Quo contact.

Update Task

Replace both the title and description of an existing Quo task.

Update Webhook

Partially update a unified Quo webhook.

FRAMEWORKS

How to build Quo MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Quo MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Quo MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Quo MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Quo MCP with Claude Cowork

Codex logo

Codex

Use Quo MCP with Codex

OpenClaw logo

OpenClaw

Use Quo MCP with OpenClaw

Hermes logo

Hermes

Use Quo MCP with Hermes

CLI logo

CLI

Use Quo MCP with CLI

Google ADK logo

Google ADK

Use Quo MCP with Google ADK

LangChain logo

LangChain

Use Quo MCP with LangChain

Mastra AI logo

Mastra AI

Use Quo MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Quo MCP with LlamaIndex

CrewAI logo

CrewAI

Use Quo MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Quo.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Quo 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