How to integrate Nango MCP with OpenAI Agents SDK

This guide walks you through connecting Nango to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Nango agent that can list all connected crm accounts, trigger manual sync with salesforce provider, get configuration for all available scripts through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Nango account through Composio's Nango MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Nango logoNango
Api Key

Nango is a unified API platform that connects to 250+ SaaS apps across CRM, HR, and accounting. Streamline integrations with one API and simplify data sync across your business tools.

24 Tools

Introduction

This guide walks you through connecting Nango to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Nango agent that can list all connected crm accounts, trigger manual sync with salesforce provider, get configuration for all available scripts through natural language commands.

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

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

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

The Nango MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Nango account. It provides structured and secure access to your integrations, so your agent can perform actions like triggering syncs, managing connections, listing providers, and executing workflow actions across 250+ external APIs on your behalf.

  • Connection management and discovery: Effortlessly list all your existing Nango connections, view metadata, or retrieve connection information without exposing sensitive credentials.
  • Provider information and browsing: Ask your agent to list all available providers or fetch detailed configuration info for a specific provider, making it easy to discover and set up new integrations.
  • Triggering workflow actions: Direct your agent to execute custom workflow actions by specifying the connection, provider, and action identifiers—unlocking advanced automation across connected platforms.
  • Manual sync initiation: Have your agent trigger sync processes for any established connection, ensuring your data stays up-to-date across all integrated services.
  • Script configuration retrieval: Let your agent fetch Nango scripts configuration and triggers, enabling more tailored and automated integration flows.

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

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

Trigger Nango Action

Trigger a Nango action to execute a workflow or operation.

Add Connection

Tool to add a connection with existing credentials to Nango.

List Connections

List all Nango connections without credentials.

Create Connect Session

Tool to create a new connect session with a 30-minute lifespan for enabling connection creation via Connect UI.

Create Integration

Tool to create a new integration in Nango.

Delete Connection

Tool to delete a specific Nango connection.

Delete Integration

Tool to delete a specific integration by its unique key.

Edit Connection

Tool to edit a connection's tags and metadata.

Get Connection with Credentials

Retrieve a specific connection with its credentials.

Get Environment Variables

Tool to retrieve environment variables from the Nango dashboard.

Get Integration

Retrieve detailed configuration for a specific Nango integration by its unique key.

Proxy GET Request

Tool to make a GET request with Nango's Proxy to forward requests to external APIs while managing authentication.

Get Sync Status

Tool to get the status of specified sync(s) for a connection or all connections.

List Connections

Tool to list all connections without credentials.

List Integrations

Tool to retrieve a list of all configured integrations.

Get Provider Details

Retrieve detailed configuration for a specific Nango provider by its unique key.

List Providers

Tool to retrieve a list of all available providers.

Proxy PUT Request

Tool to make a PUT request with the Nango Proxy to forward requests to external APIs while managing authentication.

Reconnect Session

Create a new connect session to reconnect to a specific integration.

Get Integration Functions Configuration

Retrieve all integration functions configuration from Nango.

Set Connection Metadata

Tool to set custom metadata for one or more Nango connections.

Trigger Sync

Tool to trigger sync process(es) manually.

Update Connection Metadata

Tool to edit custom metadata for one or multiple connections.

Update Integration

Tool to update an existing integration's configuration.

FAQ

Frequently asked questions

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

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

Start with Nango.It takes 30 seconds.

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

Start building