How to integrate Instagram MCP with OpenAI Agents SDK

This guide walks you through connecting Instagram to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Instagram agent that can get analytics for last week's posts, list your most recent instagram photos, fetch comments on your latest post through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Instagram account through Composio's Instagram MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Instagram logoInstagram
Oauth2

Instagram is a social platform for sharing photos, videos, and stories with your audience. It helps brands and creators engage, grow, and analyze their online presence.

29 Tools

Introduction

This guide walks you through connecting Instagram to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Instagram agent that can get analytics for last week's posts, list your most recent instagram photos, fetch comments on your latest post through natural language commands.

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

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

Also integrate Instagram with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Instagram
  • Configure an AI agent that can use Instagram as a tool
  • Run a live chat session where you can ask the agent to perform Instagram operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Instagram MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Instagram Business or Creator account. It provides structured and secure access to your Instagram content and analytics, so your agent can publish posts, analyze insights, fetch comments, manage conversations, and more—all on your behalf.

  • Automated post and carousel publishing: Let your agent draft and publish single-photo, video, or multi-image carousel posts to your feed with ease.
  • Real-time comments retrieval: Ask your agent to fetch and organize comments from any of your Instagram posts, making it simple to engage with your audience.
  • Insightful analytics and reporting: Request detailed insights on individual posts or your entire account, including impressions, reach, and engagement metrics.
  • Direct message conversation management: Retrieve details about your Instagram DM conversations, including participants and recent messages, to help you stay connected.
  • Profile and media access: Instantly fetch your profile details, statistics, and all media you've posted—photos, videos, and reels—so your agent can reference or repurpose your content.

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 starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Instagram project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Instagram.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Instagram
const session = await composio.create(userId as string, {
  toolkits: ['instagram'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only instagram.
  • The router checks the user's Instagram connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Instagram.
  • This approach keeps things lightweight and lets the agent request Instagram tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Instagram. Help users perform Instagram operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Instagram and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Instagram operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Instagram.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Instagram and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['instagram'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Instagram. Help users perform Instagram operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Instagram MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Instagram.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Create Carousel Container

Create a draft carousel post with multiple images/videos before publishing.

Delete Comment

Tool to delete a comment on Instagram media.

Delete Messenger Profile

Tool to delete messenger profile settings for an Instagram account.

Get Conversation

Get details about a specific Instagram DM conversation (participants, etc).

Get IG Comment Replies

Get replies to a specific Instagram comment.

Get Instagram Media

Get a published Instagram Media object (photo, video, story, reel, or carousel).

Get IG Media Children

Tool to get media objects (images/videos) that are children of an Instagram carousel/album post.

Get IG Media Comments

Tool to retrieve comments on an Instagram media object.

Get IG Media Insights

Tool to get insights and metrics for Instagram media objects (photos, videos, reels, carousel albums).

Get IG User Content Publishing Limit

Get an Instagram Business Account's current content publishing usage.

Get IG User Live Media

Get live media objects during an active Instagram broadcast.

Get IG User Media

Get Instagram user's media collection (posts, photos, videos, reels, carousels).

Get IG User Stories

Get active story media objects for an Instagram Business or Creator account.

Get IG User Tags

Get Instagram media where the user has been tagged by other users.

Get Messenger Profile

Get the messenger profile settings for an Instagram account.

Get Page Conversations

Get Instagram conversations for a Page connected to an Instagram Business account.

Get User Info

Get Instagram Business Account info including profile details and statistics.

Get User Insights

Get Instagram account-level insights and analytics (profile views, reach, follower count, etc.

List All Conversations

List all Instagram DM conversations for the authenticated user.

List All Messages

List all messages from a specific Instagram DM conversation.

Mark Seen

Mark Instagram DM messages as read/seen for a specific user.

Post IG Comment Replies

Tool to create a reply to an Instagram comment.

Post IG Media Comments

Tool to create a comment on an Instagram media object.

Post IG User Media

Tool to create a media container for Instagram posts.

Publish IG User Media

Tool to publish a media container to an Instagram Business account.

Reply to IG User Mentions

Tool to reply to a mention of your Instagram Business or Creator account.

Send Image

Send an image via Instagram DM to a specific user.

Send Text Message

Send a text message to an Instagram user via DM in an existing conversation.

Update Messenger Profile

Tool to update the messenger profile settings for an Instagram account.

FAQ

Frequently asked questions

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

Yes, you can. OpenAI Agents SDK 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 Instagram tools.

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

Start with Instagram.It takes 30 seconds.

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

Start building