How to integrate Aircall MCP with Vercel AI SDK v6

This guide walks you through connecting Aircall to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Aircall agent that can manage calls, search contacts, update teams, organize phone numbers, and apply tags through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Aircall account through Composio's Aircall 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
Aircall logoAircall
Oauth2Basic

Aircall is a cloud-based phone and call-center platform for business communications. It centralizes calls, contacts, teams, numbers, and tags in one place.

48 Tools

Introduction

This guide walks you through connecting Aircall to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Aircall agent that can manage calls, search contacts, update teams, organize phone numbers, and apply tags through natural language commands.

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

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

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

The Aircall MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Aircall account. It provides structured and secure access to your Aircall calls, users, teams, phone numbers, contacts, tags, and webhooks, so your agent can place calls, search call activity, manage contacts and teams, check user availability, and control call features on your behalf.

  • Call handling and insight: Have your agent place outbound calls, find calls by direction, user, phone number, tags, or date, add comments, manage recording during ongoing calls, delete call audio, and publish insight cards for call agents.
  • Contact management: Let the agent search, create, view, and delete shared contacts, then add or remove their phone numbers and email addresses.
  • User and team administration: Direct your agent to list, create, view, and delete users, create or remove teams, change team membership, and check user availability.
  • Phone numbers and tags: Instruct your agent to list and inspect Aircall phone numbers, check registration status, and create, view, list, or delete call tags.
  • Webhook management: Have your agent create, list, inspect, or delete Aircall webhooks for connected HTTPS destinations.

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: ["aircall"],
  });

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

  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 aircall, 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 Aircall 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 Aircall action and event your agent gets out of the box.

Add Contact Method

Add a phone number or an email address to an existing Aircall contact.

Add User to Team

Add a User to a Team (membership change).

Add Comment to Call

Add a comment/note to a Call (max 5 comments per call; emojis are stripped).

Create Contact

Create a shared Aircall contact.

Create Tag

Create a Tag.

Create Team

Create a new Team.

Create User

Create an Aircall user and send them a real invitation email, consuming a licensed seat.

Create Webhook

Create an Aircall webhook targeting a public HTTPS URL.

Delete Call Media

Request permanent deletion of a Call's audio recording or voicemail, for compliance or data governance.

Delete Contact

Permanently delete a shared Contact and all of its phone numbers and email addresses.

Delete Contact Method

Permanently remove one phone number or email address from an Aircall contact.

Delete Tag

Delete a Tag by id.

Delete Team

Delete a Team by id.

Delete User

Permanently delete a User.

Delete Webhook

Permanently delete an Aircall webhook.

Get Call

Retrieve a single Call by id, with optional contact / short-url / timeline enrichment via the fetch_* flags.

Get Company

Retrieve information about the connected Aircall company (name, users_count, numbers_count).

Get Contact

Retrieve a single shared Contact by id, with its nested phone_numbers[] and emails[].

Get Number

Retrieve a single Aircall phone Number by its numeric id.

Get Number Registration Status

Check whether an Aircall phone number is registered for compliance (10DLC or other regulatory registration) by reading the `status` field.

Get Tag

Retrieve a single Tag by id.

Get Team

Retrieve a single Team by id, including its member users.

Get User

Retrieve one Aircall user by numeric id or by email address.

Get User Availability

Check the current availability of one User.

Get Webhook

Retrieve one Aircall webhook by its UUID or legacy numeric id.

List Calls

List the account's calls in chronological order, covering about 6 months of history and at most 10,000 items via pagination.

List Contacts

List all shared Contacts (hard-capped at 10,000 items via pagination — window past with the `from` timestamp).

List Numbers

List all Aircall phone Numbers in the account.

List Tags

List all Tags in the account.

List Teams

List all Teams in the account.

List User Numbers (V2)

List all Aircall Numbers assigned to a specific User (V2, paginated).

List Users

List the users in the Aircall account, one page at a time with a next_cursor to continue.

List Users Availability

List the detailed availability of all Users (whether each user is available/offline/on a call, etc.

List Webhooks

List webhook subscriptions accessible to the connected Aircall company.

Publish Call Insight Card

Display contextual title, short text, links, or Aircall user details to the agent handling an ongoing call.

Remove User from Team

Remove a User from a Team (membership change).

Search Calls

Find calls matching any combination of direction (inbound or outbound), user_id, phone_number and tag ids, optionally narrowed to a from/to date window.

Search Contacts

Search shared Contacts by phone_number and/or email (optionally within a from/to date window).

Set Call Recording State

Pause or resume recording on an ongoing Aircall call.

Start Outbound Call

Place a real, billable outbound phone call from an Aircall user's desktop Workspace to an external number.

Tag Call

Tag a Call with one or more existing Tag ids (create tags first with AIRCALL_CREATE_TAG).

Transfer Call

Cold-transfer a call that is live right now to one user, one team, or one external phone number.

Update Contact

Update a Contact's core fields (first_name, last_name, company_name, information).

Update Contact Method

Update one phone number or email address that is already on an Aircall contact.

Update Number

Update at least one mutable Number field: name changes its display name; availability_status changes the first Time Rule widget and can open or close call routing; live_recording_activated enables or disables inbound and outbound recording, and audio missed while disabled cannot be recovered; priority changes routing priority; messages replaces or clears supplied Music & Messages audio slots heard by live callers.

Update Tag

Update a Tag (PUT, full replace).

Update User

Update an existing Aircall user's name, availability_status, substatus, roles or wrap-up time in place.

Update Webhook

Update an Aircall webhook's URL, name, active state, or event subscriptions.

FRAMEWORKS

How to build Aircall MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Aircall MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Aircall MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Aircall MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Aircall MCP with Claude Cowork

Codex logo

Codex

Use Aircall MCP with Codex

OpenClaw logo

OpenClaw

Use Aircall MCP with OpenClaw

Hermes logo

Hermes

Use Aircall MCP with Hermes

CLI logo

CLI

Use Aircall MCP with CLI

Google ADK logo

Google ADK

Use Aircall MCP with Google ADK

LangChain logo

LangChain

Use Aircall MCP with LangChain

Mastra AI logo

Mastra AI

Use Aircall MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Aircall MCP with LlamaIndex

CrewAI logo

CrewAI

Use Aircall MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Aircall.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Aircall 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