How to integrate Skyfire MCP with OpenAI Agents SDK

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

Introduction

This guide walks you through connecting Skyfire to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Skyfire agent that can check my skyfire wallet balance now, issue a pay token for $10 to buy service, list all ai services available for purchase, audit charges made against my last token through natural language commands.

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

The Skyfire MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Skyfire account. It provides structured and secure access to your autonomous payment and transaction infrastructure, so your agent can create tokens, pay for services, check balances, audit charges, and discover available AI-powered services on your behalf.

  • Autonomous service payments: Let your agent issue payment tokens and seamlessly pay for AI services or digital goods without manual intervention.
  • Wallet balance and charge auditing: Have your agent check buyer wallet balances before transactions and audit token charges to track exactly what was spent and when.
  • Discovery of AI and digital services: Enable your agent to browse, filter, and retrieve detailed info about available services using tags or seller agents, streamlining selection and integration.
  • Token management and automation: Allow your agent to create, manage, and charge Skyfire tokens (KYA, PAY, KYA+PAY), handling sophisticated payment flows programmatically.
  • Service details and compliance checks: Instruct your agent to fetch detailed service terms, API specs, and integration URLs—helping ensure compliance and smooth onboarding before making purchases.

Supported Tools & Triggers

Tools
Charge Skyfire TokenCharge a buyer's token (seller-side operation).
Create Skyfire KYA+PAY TokenIssue a skyfire kya+pay token (post /api/v1/tokens with type=kya+pay).
Create Skyfire KYA TokenIssue a skyfire kya token (post /api/v1/tokens with type=kya).
Create Skyfire PAY TokenIssue a skyfire pay token (post /api/v1/tokens with type=pay).
Get All Skyfire Service TagsFetch all service tags to discover filtering options.
Get Skyfire Buyer Wallet BalanceRetrieve buyer wallet balance.
Get Skyfire Service DetailsGet full details for one service.
Get Skyfire Services by AgentBrowse all services from one seller agent.
Get Skyfire Services by TagsFilter services by tags to find exactly what you need.
Get Skyfire Token ChargesAudit charges for a specific token.
Introspect Skyfire TokenCheck if a token is still valid before calling a seller service.
List Skyfire Buyer TokensInspect buyer tokens for observability.
List Skyfire Directory ServicesBrowse skyfire's service directory to obtain `sellerserviceid` for token creation.

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 Skyfire 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 Skyfire.

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 Skyfire Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["skyfire"]
)

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

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 Skyfire MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Skyfire MCP with Claude Agent SDK

Google ADK

Google ADK

Use Skyfire MCP with Google ADK

LangChain

LangChain

Use Skyfire MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Skyfire MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Skyfire MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Skyfire MCP with LlamaIndex

CrewAI

CrewAI

Use Skyfire MCP with CrewAI

Claude Code

Claude Code

Use Skyfire MCP with Claude Code

Codex

Codex

Use Skyfire MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Skyfire 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 Skyfire 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