How to integrate Fly MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Framework Integration Gradient
Fly Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Fly to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Fly agent that can deploy latest image to fly in tokyo, list all running fly apps by region, scale up my fly app to 3 instances through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Fly account through Composio's Fly 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 Fly
  • Configure an AI agent that can use Fly as a tool
  • Run a live chat session where you can ask the agent to perform Fly 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 Fly MCP server, and what's possible with it?

The Fly MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fly account. It provides structured and secure access so your agent can perform Fly operations on your behalf.

Supported Tools & Triggers

Tools
Add WireGuard PeerTool to add a WireGuard peer connection to a Fly.
Check App Name AvailabilityTool to validate an app name for Fly.
Check JobsExecute GraphQL queries against the Fly.
Check User Only TokenCheck whether the authentication token only allows user access.
Create Health Check JobTool to create a health check job for monitoring application endpoints in Fly.
Create Check Job RunTriggers a run of an existing health check job on Fly.
Create Delegated WireGuard TokenTool to create a delegated WireGuard token for peer management in a Fly.
Create Third-Party ConfigurationTool to create a third-party service configuration for discharging macaroon caveats.
Delete Delegated WireGuard TokenTool to delete a delegated WireGuard token from a Fly.
Delete OrganizationTool to delete a Fly.
Delete Remote BuilderTool to delete a remote builder configuration for a Fly.
Delete Third Party ConfigurationTool to delete a third-party service configuration from Fly.
Detach Postgres ClusterTool to detach a Postgres cluster from a Fly.
Establish SSH KeyTool to establish an SSH key for a Fly.
Fetch Nodes by IDsFetches a list of node objects from Fly.
Get Add-OnTool to find a Fly.
Get Add-On ProviderTool to query information about a specific Fly.
Get app detailsTool to retrieve detailed information about a specific Fly.
Get CertificateTool to retrieve a certificate by its ID from Fly.
Get Current Token InfoTool to get information about the current authentication token.
Get Latest Image DetailsTool to retrieve the latest available tag details for a given image repository from Fly.
Get Latest Image TagTool to retrieve the latest available image tag for a Fly.
Get MachineTool to get a single machine by ID from Fly.
Get Nearest RegionTool to retrieve the nearest Fly.
Get Node by IDTool to fetch an object by its globally unique ID using Fly.
Get OrganizationTool to find a Fly.
Get Personal OrganizationTool to retrieve the user's personal organization details from Fly.
Get PlacementsTool to get placement recommendations for Machines in Fly.
Get Platform InformationTool to retrieve Fly.
Get Products and PricingTool to retrieve Fly.
Get RegionsTool to get the list of available Fly.
Get Viewer InfoTool to retrieve the authenticated user's account information from Fly.
Issue CertificateTool to issue an SSH certificate for accessing Fly.
List Add-On PlansTool to list available add-on service plans from Fly.
List Add-OnsTool to list add-ons associated with an organization in Fly.
List AppsTool to list all Fly Apps in an organization.
List Apps via GraphQLList all Fly.
Check LocationsRetrieve all available Fly.
List MachinesTool to list Fly.
List Organization MachinesTool to list all Machines across all apps in a Fly organization.
Remove WireGuard PeerTool to remove a WireGuard peer connection from a Fly.
Set Apps V2 DefaultTool to configure whether new apps in an organization use Apps V2 by default on Fly.
Update Third-Party ConfigurationTool to update an existing third-party service configuration for discharging macaroon caveats.
Validate ConfigTool to validate a Fly.
Validate WireGuard PeersTool to validate WireGuard peer IP addresses in a Fly.

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 Fly 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 Fly.

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 Fly Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["fly"]
)

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 fly.
  • The router checks the user's Fly connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Fly.
  • This approach keeps things lightweight and lets the agent request Fly 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 Fly. "
        "Help users perform Fly 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 Fly 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 Fly 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 Fly.
  • 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 Fly 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=["fly"]
)
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 Fly. "
        "Help users perform Fly 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 Fly MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Fly.

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 Fly MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Fly MCP with Claude Agent SDK

Google ADK

Google ADK

Use Fly MCP with Google ADK

LangChain

LangChain

Use Fly MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Fly MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Fly MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Fly MCP with LlamaIndex

CrewAI

CrewAI

Use Fly MCP with CrewAI

Claude Code

Claude Code

Use Fly MCP with Claude Code

Codex

Codex

Use Fly MCP with Codex

FAQ

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

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

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

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

Used by agents from

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