How to integrate OneUp MCP with OpenAI Agents SDK

This guide walks you through connecting OneUp to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working OneUp agent that can create social posts, upload media, edit scheduled posts, comment on posts, and analyze engagement through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a OneUp account through Composio's OneUp MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

OneUp logoOneUp
Api Key

OneUp is a social media management platform for scheduling posts, comments, accounts, media, and analytics. Use it to manage multiple social networks from one place and keep publishing consistent.

27 Tools

Introduction

This guide walks you through connecting OneUp to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working OneUp agent that can create social posts, upload media, edit scheduled posts, comment on posts, and analyze engagement through natural language commands.

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

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

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

The OneUp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your OneUp account. It provides structured and secure access to your social accounts, posts, comments, media, and analytics, so your agent can schedule content, manage conversations, review performance, organize accounts, and discover trending sounds on your behalf.

  • Social post creation and scheduling: Have your agent create text, image, or video posts as drafts, scheduled content, or timeslot posts for selected social accounts.
  • Post management and recovery: Direct your agent to list posts, edit or delete scheduled content, and reschedule failed posts for a future date and time.
  • Comment and review management: Let the agent refresh and review comment threads, publish comments and replies, delete comments, and check Google Business Profile reviews.
  • Social and advertising analytics: Instruct your agent to review account performance, audience demographics, individual content results, and Meta Ads analytics, or request updated analytics across connected accounts.
  • Account and content discovery: Have your agent check connected account health, browse account categories, find Instagram or TikTok trending sounds, and list Pinterest boards or YouTube playlists.

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

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

Comment On Post

Publish a new top-level comment on a social post through a connected OneUp social account.

Create Image Post

Create a scheduled, timeslot, or draft image post for selected OneUp social accounts.

Create Media Upload URL

Create a temporary OneUp media upload URL and return instructions for a separate direct upload.

Create Text Post

Create a scheduled, timeslot, or draft text post for selected OneUp social accounts.

Create Video Post

Create a scheduled, timeslot, or draft video post for selected OneUp social accounts.

Delete Comment

Permanently and irreversibly delete a social-platform comment and its local OneUp record.

Delete Scheduled Post

Permanently and irreversibly delete an unpublished scheduled OneUp post.

Edit Scheduled Post

Replace the content and optionally the title of a scheduled OneUp post.

Get Analytics Overview

Get account-level overview metrics and ranked performance for a connected account on a supported social platform.

Get Audience Demographics

Get audience demographics for a connected Facebook, Instagram, TikTok, or YouTube account for a preset or custom reporting period.

Get Content Analytics

Get per-post, Reel, or Story analytics for a connected account on a supported social platform.

Get Google Business Reviews

Get Google Business Profile reviews and aggregate rating information for a connected account or location.

Get Meta Ads Analytics

Get campaign, ad-set, or individual-ad analytics for a connected Meta Ads account.

List Categories

List OneUp categories used to group connected social accounts.

List Category Accounts

List social accounts assigned to a OneUp category.

List Comment Replies

Fetch child replies for a parent social-platform comment.

List Comment Threads

List social posts with top-level comments and child replies in the requested order, one page at a time.

List Instagram Trending Sounds

Search Instagram trending sounds for a Facebook-connected Instagram Business or Creator account.

List Pinterest Boards

List boards available to a connected Pinterest username for post targeting.

List Posts

List scheduled, published, or failed OneUp posts, one page at a time.

List Social Accounts

List all connected OneUp social accounts and their connection health.

List TikTok Trending Sounds

Get TikTok trending commercial sounds for a documented country, period, genre, and connected TikTok account.

List YouTube Playlists

List playlists for a connected YouTube channel.

Refresh Analytics

Start a background refresh of analytics for all connected social accounts.

Refresh Comments

Start a background refresh of comments from connected social platforms.

Reply To Comment

Publish a direct reply to an existing social-platform comment.

Reschedule Failed Post

Move a failed post back into the schedule at a future date and time.

FAQ

Frequently asked questions

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

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

Start with OneUp.It takes 30 seconds.

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

Start building