SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Whatsapp MCP with LlamaIndex

Connect LlamaIndex to Whatsapp MCP. Send contact card to new lead, get business profile details for support, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Whatsapp logoWhatsapp
Oauth2Api Key

WhatsApp is a business messaging platform for secure, automated customer communication. It streamlines chat workflows and customer outreach using the WhatsApp Business API.

58 Tools1 Triggers

Introduction

This guide walks you through connecting Whatsapp to LlamaIndex using the Composio tool router. By the end, you'll have a working Whatsapp agent that can send contact card to new lead, get business profile details for support, list all approved message templates through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Whatsapp account through Composio's Whatsapp MCP server.

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

Also integrate Whatsapp with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexKimi CodeGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessCLIGoogle ADKLangChainVercel AI SDKMastra AICrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Whatsapp
  • Connect LlamaIndex to the Whatsapp MCP server
  • Build a Whatsapp-powered agent using LlamaIndex
  • Interact with Whatsapp through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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

The WhatsApp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your WhatsApp account. It provides structured and secure access to your WhatsApp Business account settings, profiles, templates, flows, and phone configuration, so your agent can manage business details, register phone numbers, maintain templates, update flows, and review account settings on your behalf.

  • Business profile management: Have your agent update your business description, contact information, and other WhatsApp Business profile settings.
  • Phone number administration: Direct your agent to register or deregister a WhatsApp Business phone number and set its two-step verification PIN.
  • Message template management: Let the agent browse the template library and create or update templates for your WhatsApp Business account.
  • Flow and commerce configuration: Instruct your agent to review Flow assets, update Flow configurations, and check commerce settings for your business phone number.
  • Account oversight and access: Have your agent review owned or shared business accounts, inspect compliance and encryption details, manage assigned user access, and subscribe your application to account notifications.

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 step10 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Whatsapp account and project
  • Basic familiarity with async Python/Typescript
2

Getting API Keys for OpenAI, Composio, and Whatsapp

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID
3

Installing dependencies

npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv

Create a new Typescript project and install the necessary dependencies:

  • @composio/llamaindex: Composio's LlamaIndex integration
  • @llamaindex/openai: OpenAI LLM integration
  • @llamaindex/tools: MCP client for LlamaIndex
  • @llamaindex/workflow: Workflow framework for LlamaIndex
  • dotenv: Environment variable management
4

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Whatsapp access
5

Import modules

import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

Create a new file called whatsapp_llamaindex_agent.ts and import the required modules:

Key imports:

  • dotenv.config loads .env at runtime
  • readline gives us a simple CLI chat loop
  • Composio is the main Composio SDK client
  • mcp connects to an MCP endpoint
  • createAgent builds a LlamaIndex agent
  • openai configures the LLM backend
6

Load environment variables and initialize Composio

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

7

Create a Tool Router session and build the agent function

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["whatsapp"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Whatsapp actions." ,
    llm,
    tools,
  });

  return agent;
}

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, whatsapp)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Whatsapp tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
8

Create an interactive chat loop

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

What's happening:

  • We're creating a direct terminal interface to chat with Whatsapp
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • The agent processes the request, selects appropriate Whatsapp tools, and returns a result
  • We extract the answer from the result data structure and display it to the user
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are streamed in a clear, readable format
9

Define the main entry point

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Whatsapp
10

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Whatsapp, then start asking questions.

Complete Code

Here's the complete code to get you started with Whatsapp and LlamaIndex:

import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["whatsapp"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Whatsapp actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();

Conclusion

You've successfully connected Whatsapp to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Whatsapp tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.
TOOLS & TRIGGERS

Supported Tools and Triggers

Every Whatsapp action and event your agent gets out of the box.

Block WhatsApp Users

Block one or more WhatsApp users to prevent them from sending messages to your business phone number.

Configure WhatsApp Conversational Automation

Configure conversational automation settings for a WhatsApp Business phone number.

Create WhatsApp Flow

Create a new WhatsApp Flow for the WhatsApp Business Account.

Create WhatsApp Max Price Agreement

Create a max price agreement for WhatsApp marketing messages pricing.

Create message template

Create a new message template for the WhatsApp Business Account.

Create QR Code

Create a new QR code with a prefilled message for a WhatsApp Business phone number.

Create upload session for WhatsApp

Create a resumable upload session for large file uploads to WhatsApp.

Delete WhatsApp Media

Delete a WhatsApp media file previously uploaded via the Media API.

Delete message template

Delete a message template from the WhatsApp Business Account by name.

Delete QR Code

Delete a specific QR code from a WhatsApp Business phone number.

Deregister WhatsApp Business Phone Number

Deregister a WhatsApp Business phone number from the Cloud API.

Get WhatsApp Business Account Activities

Retrieve activity history for a WhatsApp Business Account.

Get WhatsApp Business Account Details

Retrieve comprehensive details about a WhatsApp Business Account (WABA).

Get WhatsApp Business Compliance Info

Retrieve comprehensive business compliance information for a WhatsApp Business phone number.

Get Business Encryption

Retrieve the WhatsApp Business public key and its signature verification status.

Get business profile

Get the business profile information for a WhatsApp Business phone number.

Get client WhatsApp Business Accounts

Retrieve WhatsApp Business Accounts shared with or managed by a business portfolio.

Get WhatsApp Commerce Settings

Get commerce settings for a WhatsApp Business phone number.

Get Flow Assets

List assets associated with a WhatsApp Flow.

Get Join Requests

Get all pending join requests for a WhatsApp group.

Get media info

Get metadata and download URL for uploaded WhatsApp media.

Get WhatsApp Message History

Retrieve message history for a WhatsApp Business phone number.

Get message templates

Get all message templates for the WhatsApp Business Account.

Get owned WhatsApp Business Accounts

Retrieve WhatsApp Business Accounts owned by a business portfolio.

Get phone number

Retrieve detailed information about a specific WhatsApp Business phone number.

Get phone numbers

Retrieve all phone numbers registered to your WhatsApp Business Account.

Get WhatsApp Schedules

Retrieve campaign schedules associated with a WhatsApp Business Account.

Get WhatsApp Cloud API Settings

Get Cloud API settings for a WhatsApp Business phone number.

Get Subscribed Apps

Get all applications currently subscribed to webhooks for a WhatsApp Business Account.

Get message template library

Browse the pre-built message template library for WhatsApp Business Account.

Get template status

Get the status and details of a specific message template.

List WhatsApp Flows

List all WhatsApp Flows associated with the WhatsApp Business Account.

List WhatsApp Groups

List all WhatsApp groups associated with a business phone number.

List qr codes

Get a list of all QR codes for a WhatsApp Business phone number.

List WhatsApp Solutions

Retrieve a paginated list of Multi-Partner Solutions for a WhatsApp Business Account.

Publish WhatsApp Flow

Publish a WhatsApp Flow to make it available for use.

Register WhatsApp Business Phone Number

Register a WhatsApp Business phone number for use with WhatsApp Cloud API.

Remove Assigned User from WhatsApp Business Account

Remove a user's access from the WhatsApp Business Account.

Send contacts

Send contacts WhatsApp number.

Send interactive buttons

Send an interactive button message with up to 3 reply buttons to a WhatsApp user.

Send interactive list

Send an interactive list message to a WhatsApp number.

Send location

Send a location message with coordinates, name, and address to a WhatsApp user.

Send media

Send a media message to a WhatsApp number.

Send media by

Send media using a media ID from previously uploaded media.

Send message

Send a text message to a WhatsApp user.

Send template message

Send a template message to a WhatsApp number.

Set WhatsApp Two-Step Verification PIN

Set or reset the two-step verification PIN for a WhatsApp Business phone number.

Subscribe to WABA Webhooks

Subscribe your application to receive webhook notifications for a WhatsApp Business Account (WABA).

Unsubscribe from WABA Webhooks

Unsubscribe your application from webhook events for a WhatsApp Business Account (WABA).

Update WhatsApp Flow Metadata

Update metadata for a WhatsApp Flow including its name, categories, and endpoint URI.

Update WhatsApp Business Profile

Update WhatsApp Business Profile information including business details, contact information, and profile settings.

Update WhatsApp commerce settings

Set or update commerce settings for a WhatsApp Business phone number.

Update Flow JSON

Update the Flow JSON configuration for a WhatsApp Flow.

Update WhatsApp Cloud API Settings

Update Cloud API settings for a WhatsApp Business phone number.

Upload media

Upload media files (images, videos, audio, documents, stickers) to WhatsApp servers.

Upsert message template

Create or update a message template for the WhatsApp Business Account.

Verify Phone Number OTP Code

Verify the OTP code for a pre-verified phone number.

Who Am I

Return the identity (name) of the connected WhatsApp (Meta) account.

FRAMEWORKS

How to build Whatsapp MCP Agent with another framework

Claude Code logo

Claude Code

Use Whatsapp MCP with Claude Code

Cursor logo

Cursor

Use Whatsapp MCP with Cursor

ChatGPT logo

ChatGPT

Use Whatsapp MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Whatsapp MCP with Claude Cowork

Antigravity logo

Antigravity

Use Whatsapp MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Whatsapp MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Whatsapp MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Whatsapp MCP with Grok Bot

Muse logo

Muse

Use Whatsapp MCP with Muse

Codex logo

Codex

Use Whatsapp MCP with Codex

Kimi Code logo

Kimi Code

Use Whatsapp MCP with Kimi Code

Grok Build logo

Grok Build

Use Whatsapp MCP with Grok Build

VS Code logo

VS Code

Use Whatsapp MCP with VS Code

OpenCode logo

OpenCode

Use Whatsapp MCP with OpenCode

OpenClaw logo

OpenClaw

Use Whatsapp MCP with OpenClaw

Hermes logo

Hermes

Use Whatsapp MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Whatsapp MCP with Atomic Agent

Pi logo

Pi

Use Whatsapp MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Whatsapp MCP with DeepSeek Harness

CLI logo

CLI

Use Whatsapp MCP with CLI

Google ADK logo

Google ADK

Use Whatsapp MCP with Google ADK

LangChain logo

LangChain

Use Whatsapp MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Whatsapp MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Whatsapp MCP with Mastra AI

CrewAI logo

CrewAI

Use Whatsapp MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Whatsapp MCP with Pydantic AI

AutoGen logo

AutoGen

Use Whatsapp MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Whatsapp MCP server, the agents and LLMs can only access a fixed set of Whatsapp tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Whatsapp and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. LlamaIndex 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 Whatsapp tools.

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

Start with Whatsapp.It takes 30 seconds.

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

Start building