How to integrate Breeze MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Breeze Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Breeze to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Breeze agent that can create a new workspace for the design team, add john and sara to project alpha, archive completed project called website redesign, delete task card with id 1023 from project beta through natural language commands.

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

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

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 Breeze
  • Configure an AI agent that can use Breeze as a tool
  • Run a live chat session where you can ask the agent to perform Breeze operations

What is open-ai-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 Breeze MCP server, and what's possible with it?

The Breeze MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Breeze account. It provides structured and secure access to your projects, tasks, and team collaboration features, so your agent can create projects, manage cards, add team members, organize workflows, and handle workspace administration on your behalf.

  • Project creation and management: Instantly create new projects, archive completed ones, or delete projects you no longer need—keeping your workspace organized at all times.
  • Task and card automation: Have your agent create, update, or delete cards (tasks) in any project, assign due dates, and manage assignees for seamless task tracking.
  • Team and member collaboration: Easily add people to projects or remove them, ensuring the right teammates are always involved without manual overhead.
  • Workflow structuring with lists: Let your agent create new stages (lists) within projects to tailor workflows and keep every team organized by process.
  • Workspace setup and cleanup: Automate creation or deletion of workspaces to reflect your team’s evolving structure and simplify workspace administration.

Supported Tools & Triggers

Tools
Add Project PeopleTool to add people to a project.
Archive ProjectTool to archive a specific project.
Create CardTool to create a new card in a project.
CREATE_LISTTool to create a new list (stage) in a breeze project.
Create ProjectTool to create a new project in breeze.
Create WorkspaceTool to create a new workspace.
Delete CardTool to delete a specific card (task) by its id.
Delete ProjectTool to delete a specific project by id.
Delete Person from ProjectTool to delete a person from a project by user id.
Delete WorkspaceTool to delete a specific workspace by id.
Get CardTool to retrieve detailed info for a specific card (task) in a project.
GET_CARDSTool to get all cards (tasks) for a specific project.
Get ProjectTool to get a specific project by id.
Get Project PeopleTool to get all users in a project.
Get ProjectsTool to get all active projects.
Get WorkspaceTool to get a specific workspace by id.
Get WorkspacesTool to get all workspaces.
Move CardTool to move a card to a different stage or position.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Breeze project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

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.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
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 Breeze.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Breeze Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["breeze"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only breeze.
  • The router checks the user's Breeze connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Breeze.
  • This approach keeps things lightweight and lets the agent request Breeze tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Breeze. "
        "Help users perform Breeze operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "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 Breeze 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 dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Breeze operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Breeze.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Breeze and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["breeze"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Breeze. "
        "Help users perform Breeze operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Breeze MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Breeze.

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.

How to build Breeze MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Breeze MCP with Claude Agent SDK

Google ADK

Google ADK

Use Breeze MCP with Google ADK

LangChain

LangChain

Use Breeze MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Breeze MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Breeze MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Breeze MCP with LlamaIndex

CrewAI

CrewAI

Use Breeze MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Breeze MCP?

With a standalone Breeze MCP server, the agents and LLMs can only access a fixed set of Breeze tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Breeze and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

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 Breeze tools.

Can I manage the permissions and scopes for Breeze while using Tool Router?

Yes, absolutely. You can configure which Breeze 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.

How safe is my data with Composio Tool Router?

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 Breeze data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free