How to integrate iLovePDF MCP with OpenAI Agents SDK

This guide walks you through connecting iLovePDF to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working iLovePDF agent that can compress pdfs, merge your documents, split pdfs, convert images to pdf, and turn pdfs into images through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a iLovePDF account through Composio's iLovePDF MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

iLovePDF logoiLovePDF
Api Key

iLovePDF is a PDF and image processing API for converting, compressing, editing, and signing files. Use it to automate document workflows without building PDF tooling from scratch.

9 Tools

Introduction

This guide walks you through connecting iLovePDF to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working iLovePDF agent that can compress pdfs, merge your documents, split pdfs, convert images to pdf, and turn pdfs into images through natural language commands.

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

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

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

The iLovePDF MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your iLovePDF account. It provides structured and secure access to your PDF and image processing tools, so your agent can compress files, convert formats, merge documents, split PDFs, and monitor processing tasks on your behalf.

  • PDF and image compression: Have your agent compress one or more PDFs or images to reduce file sizes and return the processed files.
  • PDF and image conversion: Direct your agent to turn images into PDFs or convert PDF pages into images.
  • PDF merging: Instruct your agent to combine two or more PDFs in your chosen order and return one merged document.
  • Flexible PDF splitting: Let the agent split a PDF by page ranges or fixed intervals, or create a new document with selected pages removed.
  • Task and account management: Have your agent check processing progress, review output details and remaining allowance, or delete completed tasks and their files.

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

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

Compress Images

Compress one or more images and immediately return the resulting image or ZIP as an offloaded download.

Compress PDFs

Compress one or more PDFs and return the stored PDF or ZIP output in one workflow: task creation, ordered uploads, synchronous processing, download, and best-effort cleanup.

Convert Images to PDF

Convert one or more images into PDF output using iLovePDF's documented defaults and immediately return the generated PDF or ZIP as an offloaded download.

Convert PDF to Images

Convert a PDF using iLovePDF's default PDF-to-JPG behavior and immediately return the generated image or ZIP as an offloaded download.

Delete Task

Immediately delete an iLovePDF task and its related uploaded and processed files from the task's assigned worker.

Get Account Info

Return the connected iLovePDF project's account type and remaining processing allowance.

Get Task Status

Inspect an iLovePDF task's current state and output metadata on its assigned worker.

Merge PDFs

Merge two or more PDFs in the supplied order and return the merged file in one workflow.

Split PDF

Split one PDF by explicit ranges, fixed page intervals, or removed pages and return the resulting PDF or ZIP.

FAQ

Frequently asked questions

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

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

Start with iLovePDF.It takes 30 seconds.

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

Start building