How to integrate Zoho MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Zoho MCP. Convert new leads to contacts in crm, add a note to an existing zoho deal, and more using natural language, with authentication handled for you.

Get started for free Get a demo

Zoho

Oauth2

Zoho is a suite of cloud business apps for CRM, email marketing, and collaboration. It helps teams automate workflows and scale operations effortlessly.

57 Tools

Managed auth

Connect Zoho without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Book a call

Explore the MCP Gateway

Introduction

This guide walks you through connecting Zoho to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Zoho agent that can convert new leads to contacts in crm, add a note to an existing zoho deal, list all contacts added this week through natural language commands.

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

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

Also integrate Zoho with

Claude Code Claude Cowork OpenAI Agents SDK Claude Agent SDK Muse Codex Kimi Code OpenClaw Hermes Atomic Agent CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI Pydantic AI AutoGen

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Zoho integration
Using Composio's Tool Router to dynamically load and access Zoho 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 Zoho MCP server, and what's possible with it?

The Zoho MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoho account. It provides structured and secure access to your Zoho CRM data, so your agent can create contacts and leads, manage deals, search records, track activities, and draft emails on your behalf.

Contact and lead management: Have your agent create contacts and leads, find existing records, and review prospect details in Zoho CRM.
Deal and account tracking: Let the agent create and update deals, review sales opportunities, search accounts, and update account details.
Tasks, calls, and event coordination: Direct your agent to find tasks, review logged calls, create events, and check upcoming meetings.
Notes, emails, and attachments: Instruct your agent to add notes to CRM records, review related emails and attachments, and prepare email drafts.
CRM record discovery: Have your agent search across Zoho CRM modules, list available modules, and retrieve related records for added context.

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:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS

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: ["zoho"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Zoho 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 Zoho-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 Zoho 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 zoho, 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 Zoho 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 Zoho 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: ["zoho"],
  });

  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 zoho, 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 Zoho 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 Zoho action and event your agent gets out of the box.

Convert Zoho CRM Lead

Converts a lead into a contact, account, and optionally a deal in Zoho CRM.

Create Contact in Zoho CRM

Creates a new contact record in Zoho CRM.

Create Deal in Zoho CRM

Creates a new deal in Zoho CRM representing a sales opportunity with deal name, stage, amount, and closing date.

Create Email Draft in Zoho CRM

Creates email drafts for a specific record in Zoho CRM.

Create Zoho Event

Creates a new Event record in Zoho CRM.

Create Lead in Zoho CRM

Creates a new lead record in Zoho CRM with the specified details.

Create Note in Zoho CRM

Creates a new note attached to a specific record in Zoho CRM.

Create Zoho CRM Record

Creates new records in a specified module in Zoho CRM.

Create Zoho CRM Tag

Creates a new tag in Zoho CRM for a specific module.

Delete Zoho Account

Deletes an existing account record from Zoho CRM.

Delete Zoho CRM Contact

Deletes a contact from Zoho CRM.

Delete Zoho CRM Deal

Deletes a deal record from Zoho CRM.

Get Zoho CRM Account

Retrieves a specific Account record from Zoho CRM by its unique identifier.

Get Call

Retrieves a specific Call record by its unique identifier from Zoho CRM.

Get Zoho CRM Contact

Retrieves a single contact record by ID from Zoho CRM.

Get Email Drafts for Zoho CRM Record

Retrieves email drafts associated with a specific record in Zoho CRM.

Get Zoho Event

Retrieves a specific event record from Zoho CRM by its unique identifier.

Get From Addresses

Retrieves the list of from addresses configured for email operations in Zoho CRM.

Get Zoho CRM Module Fields Metadata

Retrieves field metadata for a Zoho CRM module including API names, data types, permissions, and configuration details.

Get Zoho CRM Note

Retrieves a single note by its unique identifier from Zoho CRM.

Get Zoho CRM Record Emails

Retrieves all emails associated with a specific record in Zoho CRM.

Get Zoho CRM Related Lists Metadata

Retrieves related list metadata for a Zoho CRM module to discover correct api_name values.

Get Zoho CRM Related Records

Fetch related-list records (e.

Get Zoho CRM Task

Retrieves a specific task record by its ID from Zoho CRM.

Get Zoho CRM User

Retrieves a specific user from Zoho CRM by their user ID.

Get Zoho CRM Records

Retrieves records from a specified module in Zoho CRM.

Get Zoho CRM Users

Tool to retrieve users from Zoho CRM.

List Zoho CRM Accounts

Retrieves a list of account records from Zoho CRM with pagination and filtering support.

List Zoho CRM Calls

Retrieves Call activity records from Zoho CRM with pagination support.

List Contacts

Retrieves contact records from Zoho CRM with support for pagination, filtering, and sorting.

List Deals

Retrieves a list of deals from Zoho CRM with support for filtering, sorting, and pagination.

List Zoho CRM Events

Lists events (meetings) from Zoho CRM with pagination and filtering support.

List Zoho CRM Leads

Retrieves lead records from Zoho CRM's Leads module with pagination support.

List Zoho CRM Modules

Lists all available Zoho CRM modules (standard + custom) to reliably select module API names/IDs for operations.

List Zoho CRM Notes

Retrieves a list of notes from Zoho CRM across all modules.

List Attachments for Zoho CRM Record

Tool to list attachment metadata (id, File_Name, Size, Created_Time, etc.

List Zoho CRM Tasks

Retrieves tasks from the Tasks module in Zoho CRM with support for filtering, pagination, and sorting.

Search Zoho CRM Accounts

Search for Account records within Zoho CRM using server-side queries.

Search Zoho CRM Calls

Search for Call records in Zoho CRM using server-side queries.

Search Zoho CRM Contacts

Search for contacts in Zoho CRM using server-side queries by criteria, email, phone, or keyword.

Search Deals in Zoho CRM

Search for Deal records in Zoho CRM using server-side queries.

Search Events

Search for Events in Zoho CRM using server-side queries.

Search Leads

Search for lead records in Zoho CRM using server-side queries.

Search Notes

Search for notes in Zoho CRM using server-side queries.

Search Zoho CRM Tasks

Search for tasks in Zoho CRM using flexible criteria including subject, status, priority, or due date.

Search Zoho CRM Records

Search for records within a Zoho CRM module using server-side queries.

Update Zoho CRM Account

Updates an existing Account record in Zoho CRM with the specified field values.

Update Zoho CRM Call

Updates existing call records in the Calls module in Zoho CRM.

Update Zoho CRM Deal

Updates an existing deal in Zoho CRM.

Update Zoho CRM Email Draft

Updates an existing email draft associated with a record in Zoho CRM.

Update Zoho CRM Event

Updates existing events in Zoho CRM.

Update Lead

Updates existing lead records in Zoho CRM.

Update Zoho CRM Note

Updates an existing note in Zoho CRM.

Update Related Records in Zoho CRM

Associates or updates relationships between records across different modules in Zoho CRM.

Update Zoho CRM Record

Updates existing records in a specified module in Zoho CRM.

Upload Attachment to Zoho CRM Record

Tool to upload a file as an Attachment to a specific Zoho CRM record.

Validate Zoho CRM Credentials

Validates Zoho CRM credentials by retrieving current user information.

FRAMEWORKS

How to build Zoho MCP Agent with another framework

Claude Code

Use Zoho MCP with Claude Code

Claude Cowork

Use Zoho MCP with Claude Cowork

OpenAI Agents SDK

Use Zoho MCP with OpenAI Agents SDK

Claude Agent SDK

Use Zoho MCP with Claude Agent SDK

Muse

Use Zoho MCP with Muse

Codex

Use Zoho MCP with Codex

Kimi Code

Use Zoho MCP with Kimi Code

OpenClaw

Use Zoho MCP with OpenClaw

Hermes

Use Zoho MCP with Hermes

Atomic Agent

Use Zoho MCP with Atomic Agent

CLI

Use Zoho MCP with CLI

Google ADK

Use Zoho MCP with Google ADK

LangChain

Use Zoho MCP with LangChain

Mastra AI

Use Zoho MCP with Mastra AI

LlamaIndex

Use Zoho MCP with LlamaIndex

CrewAI

Use Zoho MCP with CrewAI

Pydantic AI

Use Zoho MCP with Pydantic AI

AutoGen

Use Zoho MCP with AutoGen

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

HubSpot

Oauth2Api Key

HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place.

Pipedrive

Oauth2Api Key

Pipedrive is a sales management platform offering pipeline visualization, lead tracking, and workflow automation. It helps sales teams keep deals moving forward efficiently and never miss a follow-up.

Salesforce

Oauth2S2s Oauth2

Salesforce is a leading CRM platform that helps businesses manage sales, service, and marketing. It centralizes customer data, enabling teams to drive growth and build strong relationships.

Apollo

Api Key

Apollo is a CRM and lead generation platform that helps businesses discover contacts and manage sales pipelines. Use it to streamline customer outreach and track your deals from one place.

FAQ

Frequently asked questions

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

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

Start with Zoho.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Zoho tool your agent needs.Free to start.

Start building

How to integrate Zoho MCP with Vercel AI SDK v6

Connect Zoho without auth hassles

Introduction

Also integrate Zoho with

TL;DR

What is Vercel AI SDK?

What is the Zoho MCP server, and what's possible with it?

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

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

Complete Code

Conclusion

Supported Tools

How to build Zoho MCP Agent with another framework

Claude Code

Claude Cowork

OpenAI Agents SDK

Claude Agent SDK

Muse

Codex

Kimi Code

OpenClaw

Hermes

Atomic Agent

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Pydantic AI

AutoGen

Explore Other Toolkits

HubSpot

Pipedrive

Salesforce

Apollo

Frequently asked questions

What are the differences in Tool Router MCP and Zoho MCP?+

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

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

How safe is my data with Composio Tool Router?+

Start with Zoho.It takes 30 seconds.