How to integrate ManyReach MCP with OpenAI Agents SDK

This guide walks you through connecting ManyReach to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working ManyReach agent that can create outreach campaigns, add your prospects, build mailing lists, review messages, and manage your tags through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a ManyReach account through Composio's ManyReach MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

ManyReach logoManyReach
Api Key

ManyReach is a cold email outreach platform for campaigns, prospects, senders, messages, and workspaces. It helps teams run targeted outbound email programs from one place.

16 Tools

Introduction

This guide walks you through connecting ManyReach to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working ManyReach agent that can create outreach campaigns, add your prospects, build mailing lists, review messages, and manage your tags through natural language commands.

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

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

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

The ManyReach MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your ManyReach account. It provides structured and secure access to your outreach campaigns, prospects, mailing lists, senders, messages, tags, and workspace details, so your agent can create campaigns, organize prospects, review outreach messages, check senders, and manage tags on your behalf.

  • Campaign planning and management: Have your agent create draft campaigns, find existing campaigns by status, and update their configuration.
  • Prospect and mailing list organization: Let the agent create, find, and update prospects, then create, rename, or reorganize mailing lists for targeted outreach.
  • Message and reply review: Instruct your agent to retrieve sent messages and replies using campaign, sender, address, subject, follow-up, or CRM status filters.
  • Sender and tag management: Direct your agent to find sender mailboxes by connection or warmup state, and create, find, or update tags for prospects, campaigns, and senders.
  • Account monitoring and cleanup: Have your agent check organization details, sending credits, and data token balances, or permanently remove campaigns, prospects, mailing lists, and tags you no longer need.

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

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

Create Campaign

Create and save a new draft campaign's configuration.

Create Mailing List

Create a ManyReach mailing list.

Create Prospect

Create one ManyReach prospect.

Create Tag

Create a CRM, campaign, or sender tag.

Delete Outreach Resource

Permanently and irreversibly delete exactly one campaign, prospect, mailing list, or tag by ID.

Get Account Overview

Return the authenticated ManyReach organization together with its sending-credit and data-token balances.

List Campaigns

Find campaigns in the authenticated organization, optionally filtering by lifecycle status or archived state.

List Mailing Lists

Return one page of mailing lists available for organizing and importing prospects.

List Messages

Retrieve one read-only page of reply, sent, or manually sent messages with campaign, followup, sender, CRM-status, address, and subject filters.

List Prospects

Search and filter prospects by identity, CRM status, tags, campaign membership, and existing email-validation verdict.

List Senders

Find configured sender mailboxes by folder, connection status, warmup state, or search text.

List Tags

Find CRM, campaign, or sender tags and optionally include prospect counts.

Update Campaign

Update an existing draft campaign's configuration.

Update Mailing List

Rename or move an existing ManyReach mailing list.

Update Prospect

Update contact, personalization, list, CRM, or campaign-sending eligibility fields for one ManyReach prospect by ID.

Update Tag

Update an existing tag's title and description.

FAQ

Frequently asked questions

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

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

Start with ManyReach.It takes 30 seconds.

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

Start building