How to integrate Modem MCP with OpenAI Agents SDK

This guide walks you through connecting Modem to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Modem agent that can create company records, add your contacts, review company activity, trace histories, and check identities through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Modem account through Composio's Modem MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Modem logoModem
Api Key

Modem is a customer intelligence platform that turns conversations into structured topics, people, and company insights. Use it to analyze feedback patterns and automate customer workflows faster.

30 Tools

Introduction

This guide walks you through connecting Modem to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Modem agent that can create company records, add your contacts, review company activity, trace histories, and check identities through natural language commands.

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

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

Also integrate Modem 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 Modem
  • Configure an AI agent that can use Modem as a tool
  • Run a live chat session where you can ask the agent to perform Modem 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 Modem MCP server, and what's possible with it?

The Modem MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Modem account. It provides structured and secure access to your customer conversation topics, people, companies, channels, and activity insights, so your agent can search topics, analyze engagement, manage customer records, review histories, and organize insights on your behalf.

  • Topic discovery and analysis: Have your agent search customer conversation topics by keywords or meaning, then review summaries, classifications, priorities, participants, message groups, and history.
  • People and company insights: Let the agent find people and companies, inspect their profiles and conversation activity, and see how engagement breaks down across sources.
  • Customer record management: Direct your agent to create or update people and companies, associate people with companies, and connect external records to the right profiles.
  • Channel and activity monitoring: Instruct your agent to review connected conversation channels, message counts, company activity trends, and source-level engagement.
  • Data cleanup and topic organization: Have your agent update topic priorities or archive states, inspect change histories, and merge duplicate topics, people, or companies when needed.

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 Modem 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 Modem.
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 Modem
const session = await composio.create(userId as string, {
  toolkits: ['modem'],
});
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 modem.
  • The router checks the user's Modem connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Modem.
  • This approach keeps things lightweight and lets the agent request Modem 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 Modem. Help users perform Modem 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 Modem 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 Modem 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 Modem.
  • 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 Modem 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: ['modem'],
  });
  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 Modem. Help users perform Modem 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 Modem MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Modem.

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 Modem action and event your agent gets out of the box.

Add People to Company

Associate one or more existing people with an existing company.

Create Companies

Create one to 50 companies in one batch.

Create People

Create one to 50 people in one batch.

Get Channel

Get one channel's source details, connection state, context, timestamps, and message count by UUID.

Get Company

Get one company's core details, connection values, domain, logo, and VIP status by decimal ID.

Get Company Activity

Get one company's message count, weekly activity series, and source-level message breakdown.

Get Company History

Get up to 50 company audit records plus merge history.

Get Company Identities

Get external platform identities linked to one company by Modem's identify operation.

Get Current Organization

Return the organization selected by the connected API key.

Get Person

Get one person's complete profile, including company, connections, tags, sources, timestamps, identities, and message activity aggregates.

Get Person History

Get up to 50 person audit records plus merge history.

Get Person Identities

Get all external platform identities linked to one person.

Get Person Source Stats

Get one person's message counts broken down by source platform.

Get Topic

Get one topic's complete details, including its summary, classification, lifecycle, priority, keywords, time range, archive state, and event count.

Get Topic Groups

Get every message group assigned to one topic in ascending or descending group-time order.

Get Topic History

Get up to 50 topic audit records plus action and merge history.

Get Topic People

Get every unique person who participated in one topic, including source identities, company, profile, VIP state, and contribution count.

Identify External Records

Upsert links from external platform records to Modem people and companies in batches of 50.

List Channels

List organization channels with connection state and message counts, optionally filtered by source, name, or channel IDs.

List Companies

List companies with person and message aggregates, optionally searching and sorting the result.

List Groups

List message groups for exactly one company or one person, returning compact message content and topic context one page at a time.

List People

List people with aggregated message statistics, optionally filtering by search text, ecosystem tags, or company and sorting the result.

List and Search Topics

List or search topics by keywords or semantic meaning with organization, participant, source, status, date, and classification filters, one page at a time.

Merge Companies Irreversibly

Irreversibly merge one or more source companies into one surviving target.

Merge People Irreversibly

Irreversibly merge one or more source people into one surviving target.

Merge Topics Irreversibly

Irreversibly merge 1 to 50 source topics into one surviving target.

Update Companies

Update one to 50 companies in one batch.

Update People

Update one to 50 people in one batch.

Update Topic

Update one topic's priority, lifecycle, issue type, complete keyword list, or archive state.

Update Topics

Set priority or archive state for one to 100 topics at once.

FAQ

Frequently asked questions

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

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

Start with Modem.It takes 30 seconds.

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

Start building