How to integrate Intercom MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Intercom logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Intercom to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Intercom agent that can add tag 'vip' to contact john doe, assign open conversation #123 to support team, create note for contact emily about refund through natural language commands.

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

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

Also integrate Intercom with

TL;DR

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

The Intercom MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Intercom account. It provides structured and secure access to your customer engagement platform, so your agent can perform actions like managing conversations, tagging contacts, creating articles, and updating company records on your behalf.

  • Conversation management and assignment: Let your agent assign conversations to teams or admins, create new conversations, and close them when resolved, streamlining your support workflow.
  • Contact tagging and note creation: Effortlessly tag contacts with relevant labels or add detailed notes for context, making customer follow-ups more organized and actionable.
  • Automated company and contact updates: Enable your agent to attach contacts to companies, create or update company records, and keep your Intercom data clean and up to date.
  • Article and collection creation: Let your agent publish new articles or create help center collections to expand your self-serve support resources without manual effort.
  • Subscription and message preferences management: Allow your agent to add or manage subscriptions for contacts, helping you personalize communication and respect user preferences automatically.

Supported Tools & Triggers

Tools
Add subscription to a contactYou can add a specific subscription to a contact.
Add tag to contactTool to add a tag to a contact in Intercom.
Archive contactTool to archive a single contact in Intercom.
Assign conversationAssigns a conversation to a specific admin or team in Intercom.
Attach contact to companyTool to attach a contact to a company in Intercom.
Attach contact to conversationTool to attach a contact participant to a conversation on behalf of admin or contact.
Attach tag to conversationTool to add a tag to a specific conversation in Intercom.
Attach tag to ticketTool to add a tag to a ticket in Intercom.
Block contactTool to block a single contact in Intercom.
Cancel data exportTool to cancel an active content data export job.
Close conversationCloses a conversation in Intercom, marking it as resolved.
Create a collectionYou can create a new collection by making a POST request to `https://api.
Create an articleYou can create a new article by making a POST request to `https://api.
Create a noteYou can add a note to a single contact.
Create contactTool to create a new contact in Intercom workspace.
Create content import sourceTool to create a new content import source for the Fin Content Library.
Create conversationCreates a new conversation in Intercom.
Create data attributeTool to create a custom data attribute for contacts or companies.
Create data eventTool to submit a data event to Intercom to track user activities.
Create data exportTool to initiate an async data export job for message content.
Create external pageTool to create an external page in Fin Content Library or update an existing page by external ID.
Create help center sectionTool to create a new help center section within a collection.
Create internal articleTool to create a new internal article for team knowledge sharing.
Create or update a companyYou can create or update a company.
Create or update tagTool to create or update a tag, and optionally tag/untag companies or tag contacts.
Create ticketTool to create a ticket in Intercom to track customer requests and issues.
Create a ticket typeTool to create a new ticket type that defines the data structure for tracking customer requests.
Create ticket type attributeTool to create a new attribute for a ticket type in Intercom.
Create event summariesTool to create event summaries for a user to track event occurrences.
Delete a collectionYou can delete a single collection by making a DELETE request to `https://api.
Delete a companyYou can delete a single company.
Delete an articleYou can delete a single article by making a DELETE request to `https://api.
Delete a tagTool to delete a tag from Intercom workspace.
Delete a visitorTool to delete a visitor from the Intercom workspace.
Delete a contactTool to delete a contact from the Intercom workspace.
Delete content import sourceTool to delete a content import source and all its external pages.
Delete external pageTool to delete an external page from content library and AI answers.
Delete internal articleTool to delete a single internal article by ID.
Delete ticketTool to delete a ticket from the Intercom system.
Detach a contact from tagTool to remove a tag from a specific contact in Intercom.
Detach contact from companyTool to detach a contact from a company in Intercom.
Detach tag from conversationTool to remove a tag from a specific conversation in Intercom.
Detach tag from ticketTool to remove a tag from a ticket in Intercom.
Download data exportTool to download content data export from Intercom.
Enqueue create ticketTool to enqueue ticket creation for asynchronous processing.
Find a tagTool to retrieve details for a specific tag by its ID.
Get a contactYou can fetch the details of a single contact.
Get content import sourceTool to retrieve a content import source by its ID.
Get conversationRetrieves a specific conversation by ID with all messages and details.
Get entity countsTool to retrieve summary counts for Intercom app entities including companies, users, leads, tags, segments, and conversations.
Get custom object instance by external IDTool to retrieve a custom object instance by its external_id.
Get external pageTool to retrieve an external page from Fin Content Library by ID.
Get ticketTool to retrieve a ticket from Intercom.
Get a ticket typeTool to retrieve details for a specific ticket type by its ID.
Identify an adminYou can view the currently authorised admin along with the embedded app object (a "workspace" in legacy terminology).
Retrieve job statusTool to retrieve the status of job execution.
List all activity logsYou can get a log of activities by all admins in an app.
List all adminsYou can fetch a list of admins for a given workspace.
List all articlesYou can fetch a list of all articles by making a GET request to `https://api.
List all collectionsYou can fetch a list of all collections by making a GET request to `https://api.
List all companiesYou can list companies.
List all help centersYou can list all Help Centers by making a GET request to `https://api.
List all macrosTool to fetch a list of all macros (saved replies) in your workspace for use in automating responses.
List all notesYou can fetch a list of notes that are associated to a contact.
List attached companies for contactYou can fetch a list of companies that are associated to a contact.
List attached contactsYou can fetch a list of all contacts that belong to a company.
List attached segments for companiesYou can fetch a list of all segments that belong to a company.
List attached segments for contactYou can fetch a list of segments that are associated to a contact.
List away status reasonsTool to retrieve all away status reasons for a workspace including deleted ones.
List callsTool to list all phone calls from Intercom with pagination support.
List calls with transcriptsTool to retrieve calls by conversation IDs with transcripts when available.
List company notesTool to list all notes associated with a specific company.
List all contactsTool to list all contacts (users or leads) in your Intercom workspace with pagination support.
List content import sourcesTool to retrieve all content import sources for the workspace.
List conversationsLists all conversations from Intercom with pagination support.
List data attributesTool to list all data attributes for contacts, companies, and conversations.
List data eventsTool to retrieve a log of data events belonging to a customer.
List external pagesTool to list all external pages from Fin Content Library.
List help center sectionsTool to fetch a list of all help center sections in descending order by updated_at.
List internal articlesFetches one page of internal articles from Intercom.
List all news itemsTool to fetch a list of all news items from Intercom.
List all segmentsTool to retrieve all segments defined within a workspace for filtering and categorizing contacts.
List subscriptions for a contactYou can fetch a list of subscription types that are attached to a contact.
List subscription typesTool to list all subscription types available in the workspace.
List all tagsTool to fetch all tags for the workspace.
List tags attached to a contactYou can fetch a list of all tags that are attached to a specific contact.
List all teamsTool to retrieve all teams within a workspace.
List all ticket statesTool to fetch all ticket states for the workspace.
List all ticket typesTool to retrieve all ticket types for the workspace.
Merge a lead and a userYou can merge a contact with a `role` of `lead` into a contact with a `role` of `user`.
Register Fin Voice callTool to register a Fin Voice call with Intercom.
Remove subscription from a contactYou can remove a specific subscription from a contact.
Remove tag from a contactYou can remove tag from a specific contact.
Reopen conversationReopens a closed conversation in Intercom.
Reply to ticketTool to reply to a ticket with a message from admin or contact, or with a note for admins.
Reply to conversationSends a reply to an existing conversation in Intercom.
Retrieve a collectionYou can fetch the details of a single collection by making a GET request to `https://api.
Retrieve a company by idYou can fetch a single company.
Retrieve a help centerYou can fetch the details of a single Help Center by making a GET request to `https://api.
Retrieve job statusTool to retrieve the status of a data export job.
Retrieve a macroTool to fetch a single macro (saved reply) by its ID.
Retrieve an adminYou can retrieve the details of a single admin.
Retrieve an articleYou can fetch the details of a single article by making a GET request to `https://api.
Retrieve a segmentTool to retrieve details for a single segment by its ID.
Retrieve companiesYou can fetch a single company by passing in `company_id` or `name`.
Retrieve internal articleTool to retrieve an internal article by ID from Intercom.
Retrieve noteTool to retrieve details of a single note by its identifier.
Retrieve a teamTool to retrieve detailed information about a specific team by ID.
Retrieve visitor with user IDTool to retrieve a specific visitor's details using their user_id.
Scroll over all companiesThe `list all companies` functionality does not work well for huge datasets, and can result in errors and performance problems when paging deeply.
Search contactsTool to search for contacts using query filters with operators.
Search conversationsSearches for conversations using query string with support for filtering and sorting
Search for articlesYou can search for articles by making a GET request to `https://api.
Search internal articlesSearches one page of internal articles in Intercom.
Search ticketsTool to search tickets in Intercom by filtering attribute values.
Set admin to awayTool to set an admin to away status in Intercom.
Set an admin to awayYou can set an Admin as away for the Inbox.
Show callTool to retrieve a single call by ID from Intercom.
Show call transcriptTool to get call transcript by call ID.
Show contact by external IDTool to retrieve a contact by their external ID.
Unarchive contactTool to unarchive a previously archived contact in Intercom.
Update a collectionYou can update the details of a single collection by making a PUT request to `https://api.
Update a companyYou can update a single company using the Intercom provisioned `id`.
Update a contactYou can update an existing contact (ie.
Update an articleYou can update the details of a single article by making a PUT request to `https://api.
Update contactTool to update an existing contact in Intercom.
Update content import sourceTool to update an existing content import source in Fin Content Library.
Update data attributeTool to update an existing data attribute in Intercom.
Update external pageTool to update an existing external page in Fin Content Library.
Update internal articleTool to update an internal article with new title, body, author or owner information.
Update ticketTool to update an existing ticket in Intercom.
Update a ticket typeTool to update an existing ticket type in the workspace.
Update ticket type attributeTool to update an existing attribute for a ticket type.

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: ["intercom"],
  });

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

  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 intercom, 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 Intercom 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 Intercom MCP Agent with another framework

FAQ

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

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

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

Yes, absolutely. You can configure which Intercom 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 Intercom 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.