How to integrate Conductor MCP with OpenAI Agents SDK

This guide walks you through connecting Conductor to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Conductor agent that can create a workspace for bug triage, start a coding agent refactor session, search transcripts for failed deploy discussion through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Conductor account through Composio's Conductor MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Conductor logoConductor
Api Key

Conductor is a cloud development platform for workspaces, coding-agent sessions, messages, and transcript search. It helps teams run, review, and coordinate agent-driven development in one place.

17 Tools

Introduction

This guide walks you through connecting Conductor to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Conductor agent that can create a workspace for bug triage, start a coding agent refactor session, search transcripts for failed deploy discussion through natural language commands.

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

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

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

The Conductor MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Conductor account. It provides structured and secure access to your projects, cloud workspaces, coding-agent sessions, messages, and transcripts, so your agent can create workspaces, run sessions, exchange messages, manage workspace states, and search transcripts on your behalf.

  • Cloud workspace management: Have your agent create workspaces for available projects, check their status, rename them, or put them to sleep or archive them.
  • Coding-agent session control: Let the agent create and rename sessions, check whether they are idle, working, or in an error state, and stop current work or archive sessions.
  • Agent messaging: Direct your agent to send coding prompts to a session and read individual messages or full session conversations.
  • Transcript search and review: Instruct your agent to search session transcripts with read-only queries and find relevant details from past coding work.
  • Project and activity discovery: Have your agent list available repository projects, browse their workspaces and sessions, and review recent activity.

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

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

Change Workspace State

Put a workspace to sleep or archive it.

Create Session

Create another agent chat session in an existing workspace.

Create Workspace

Create a cloud workspace and its first agent session.

Get Current User

Return the user and organization represented by the connected Conductor API key.

Get Message

Get one transcript message by id.

Get Project

Get one Conductor project and its repository remote by project id.

Get Session

Get one agent session's configuration and current idle, working, or error status in one read.

Get Workspace

Get a workspace's metadata and current lifecycle status in one read, including initialization progress or errors.

List Messages

Read one page of a session transcript or incrementally read messages after a known message ID.

List Projects

List repositories available to the connected account for creating Conductor workspaces.

List Sessions

List one page of agent chat sessions in a Conductor workspace.

List Workspaces

List one page of workspaces belonging to a Conductor project, including deep links and recent activity.

Query Transcripts

Run one read-only SQL SELECT against the organization's session_transcripts_view.

Rename Session

Change an existing Conductor session's display name without stopping its agent.

Rename Workspace

Change the display name of an existing Conductor workspace without changing its lifecycle state.

Send Message

Send a prompt to a Conductor session agent.

Stop Session

Cancel only the current turn and queued messages, or archive the entire session.

FAQ

Frequently asked questions

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

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

Start with Conductor.It takes 30 seconds.

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

Start building