How to integrate Finerworks MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Finerworks logo
open-ai-agents-sdk logo
divider

Introduction

This guide walks you through connecting Finerworks to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Finerworks agent that can add five new artwork images to your library, list all available fine art paper types, submit a print order for three photos through natural language commands.

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

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

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

The Finerworks MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your FinerWorks account. It provides structured and secure access to your fine art and photo printing services, so your agent can perform actions like uploading artwork, managing orders, updating account info, and exploring product options on your behalf.

  • Artwork upload and management: Easily add new images to your FinerWorks library, complete with metadata and image URIs, so your inventory is always up to date.
  • Order submission and tracking: Ask your agent to submit batches of print orders or retrieve shipping options, streamlining your print fulfillment process.
  • Product and media exploration: Instantly list available product types, media types, and style options to help you select the perfect materials for your artwork.
  • Account and profile updates: Let your agent fetch or update your user profile, including business information, billing details, and payment profiles, as your needs change.
  • Credential verification and file selection: Test your credentials for peace of mind, or update which image files are selected for current projects—all without manual steps.

Supported Tools & Triggers

Tools
Add ImagesTool to add images to a finerworks library.
Get UserTool to retrieve the current user's profile.
List Media TypesTool to get available media types.
List Product TypesTool to list product types.
List Shipping Options MultipleTool to list shipping options for multiple orders.
List Style TypesTool to get a list of style types.
Submit OrdersTool to submit up to five new orders.
Test My CredentialsTool to test the configured FinerWorks credentials.
Update File SelectionTool to update a user's currently selected image files using the selection key.
Update UserTool to update various features of a user's account profile.

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

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Finerworks 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 Finerworks.

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 Finerworks Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["finerworks"]
)

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

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 Finerworks MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Finerworks MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Finerworks MCP with Claude Code

Codex logo

Codex

Use Finerworks MCP with Codex

OpenClaw logo

OpenClaw

Use Finerworks MCP with OpenClaw

CLI logo

CLI

Use Finerworks MCP with CLI

Google ADK logo

Google ADK

Use Finerworks MCP with Google ADK

LangChain logo

LangChain

Use Finerworks MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Finerworks MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Finerworks MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Finerworks MCP with LlamaIndex

CrewAI logo

CrewAI

Use Finerworks MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Finerworks 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 Finerworks 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