How to integrate ActiveMerge MCP with OpenAI Agents SDK

This guide walks you through connecting ActiveMerge to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working ActiveMerge agent that can generate invoices from saved templates, merge contract files for client signature, store signed ndas in project folders through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a ActiveMerge account through Composio's ActiveMerge MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

ActiveMerge logoActiveMerge
Api Key

ActiveMerge is a document automation platform for generating documents, images, merged files, and e-signature workflows. It helps teams turn templates and stored files into finished, shareable documents faster.

13 Tools

Introduction

This guide walks you through connecting ActiveMerge to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working ActiveMerge agent that can generate invoices from saved templates, merge contract files for client signature, store signed ndas in project folders through natural language commands.

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

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

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

The ActiveMerge MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your ActiveMerge account. It provides structured and secure access to your templates, workflows, generation jobs, credits, and stored files, so your agent can generate documents, create images, run template workflows, track generation progress, and manage generated files on your behalf.

  • Template-based document generation: Have your agent review available document templates and their required placeholders, then generate documents using your case-sensitive data.
  • Automated image creation: Let the agent inspect image templates, create images from your records, and check each generation job for progress, errors, and completed output.
  • Multi-document workflows: Direct your agent to find available workflows, collect their required placeholders, and generate documents for every template in a chosen workflow.
  • Generation tracking and credit checks: Instruct your agent to check remaining credits before starting work, then review document generation history and job status.
  • Generated file management: Have your agent browse stored files, save completed document outputs to permanent storage, and prepare stored files for download.

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

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

Generate Document

Start asynchronous document generation from a template and case-sensitive placeholder data.

Generate Images

Start an asynchronous image-generation job from inline JSON records.

Generate Workflow Documents

Generate documents for every template in an ActiveMerge workflow using case-sensitive placeholder data.

Get Credits

Get total, used, remaining, plan, and prepaid ActiveMerge credits before running credit-consuming generation tools.

Get Document Generations

Get one document-generation job by ID, or list and filter generation history when no job ID is supplied.

Get Document Template Placeholders

Return the case-sensitive placeholder names required by one document template.

Get File Download URL

Create a temporary download URL for a file in ActiveMerge cloud storage.

Get Image Generation

Get an image-generation job's progress, credit usage, errors, and temporary ZIP download URL when complete.

Get Image Templates

List image templates and basic placeholders, or get complete dimensions, positions, defaults, and styles for one template when template_id is supplied.

Get Workflows

List available ActiveMerge workflows, or return the case-sensitive placeholders for one workflow when workflow_id is supplied.

List Document Templates

List document templates available to the connected ActiveMerge account, including the unique template IDs needed for placeholder lookup and generation.

List Stored Files

List the immediate files and folders at the ActiveMerge cloud-storage root, or directly inside parent_folder_id when supplied.

Save Generated Files

Save non-expired output from a completed document-generation job to permanent ActiveMerge cloud storage.

FAQ

Frequently asked questions

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

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

Start with ActiveMerge.It takes 30 seconds.

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

Start building