How to integrate Gift up MCP with Autogen

This guide walks you through connecting Gift up to AutoGen using the Composio tool router. By the end, you'll have a working Gift up agent that can list all active gift cards sold this week, show available items for sale by group, get recent transaction reports for your store through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Gift up account through Composio's Gift up MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Gift up logoGift up
Api Key

Gift Up! is a digital platform for selling, managing, and redeeming gift cards online. It streamlines promotions and gift card transactions for businesses and their customers.

44 Tools

Introduction

This guide walks you through connecting Gift up to AutoGen using the Composio tool router. By the end, you'll have a working Gift up agent that can list all active gift cards sold this week, show available items for sale by group, get recent transaction reports for your store through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Gift up account through Composio's Gift up MCP server.

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

Also integrate Gift up with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Gift up
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Gift up tools
  • Run a live chat loop where you ask the agent to perform Gift up operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Gift up MCP server, and what's possible with it?

The Gift up MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gift Up! account. It provides structured and secure access to your gift card operations, so your agent can list available gift cards, fetch company or checkout details, generate transaction reports, and manage users or webhook subscriptions on your behalf.

  • Gift card inventory management: Instantly list, filter, and audit all gift cards issued or available in your account, including status and details.
  • Sales item and group retrieval: Let your agent fetch all items for sale and organize them by item groups, making it easy to manage or present products.
  • Company and checkout settings access: Retrieve current company details and checkout configuration to audit or display your store's gift card setup.
  • Transaction reporting and analytics: Generate and filter transaction reports for deep insights into gift card sales, redemptions, and trends.
  • User and webhook management: List all users with account access or subscribe to webhook events, enabling automated notifications and streamlined team management.

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 step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Gift up account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
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
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Gift up via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Gift up connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Gift up session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["gift_up"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Gift up tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Gift up assistant agent with MCP tools
    agent = AssistantAgent(
        name="gift_up_assistant",
        description="An AI assistant that helps with Gift up operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Gift up tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Gift up related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Gift up tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Gift up and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Gift up session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["gift_up"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Gift up assistant agent with MCP tools
        agent = AssistantAgent(
            name="gift_up_assistant",
            description="An AI assistant that helps with Gift up operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Gift up related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Gift up through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Gift up, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Gift up action and event your agent gets out of the box.

Add Note to Order

Tool to add a note to an existing order.

Create Item

Tool to create a new item for sale in the Gift Up checkout.

Create Item Group

Tool to create a new item group for organizing items in the Gift Up checkout.

Create Order

Tool to create a new order which generates one or more gift cards.

Delete Item

Tool to delete an item from the Gift Up checkout.

Delete Item Group

Tool to delete an item group by its ID.

Delete Webhook

Tool to delete a webhook subscription by its ID.

Get Checkout Settings

Tool to retrieve the current checkout settings.

Get Company Details

Tool to retrieve company details.

Get Email Settings

Tool to retrieve email settings for the Gift Up account.

Get Gift Card by Code

Tool to retrieve a gift card by its code.

Get Gift Card Settings

Tool to retrieve gift card settings including code format, expiration rules, and display options.

Get Item by ID

Tool to retrieve detailed information about a specific item by its ID.

Get Order by ID

Tool to retrieve a specific order by ID.

API Health Check

Tool to perform a health check on the Gift Up!

Get Report Transaction

Tool to retrieve a specific transaction report by its ID.

Get Shipping Settings

Tool to retrieve shipping settings for physical gift cards.

Get Stripe Connection

Tool to retrieve current Stripe integration connection settings.

Get Webhook

Tool to retrieve a specific webhook by its ID.

List Gift Card Artwork

Tool to list all gift card artwork available for use on gift cards.

List Gift Cards

Tool to list gift cards.

List Item Groups

Tool to list item groups.

List Items

Lists all items (gift cards, passes, etc.

List Locations

Retrieves all physical locations where gift cards are sold and/or redeemed.

List Promotions

Tool to list all promotions that allow discounts to be applied on the Gift Up checkout.

List Report Transactions

Tool to list report transactions with optional filters.

List GiftUp Users

Tool to list all users.

List Webhooks

Tool to list all webhooks configured for the account.

Health Check (POST)

Tool to perform a health check using POST /ping endpoint.

Reactivate Gift Card

Tool to reactivate a voided gift card.

Redeem Gift Card

Tool to redeem a specified amount or units from a gift card.

Redeem Gift Card In Full

Tool to redeem a gift card in full.

Subscribe to Webhook

Subscribe to Gift Up!

Top Up Gift Card

Tool to add value to an existing gift card.

Undo Gift Card Redemption

Tool to undo a previous redemption on a gift card, restoring the redeemed amount to the gift card balance.

Update Email Settings

Tool to update email settings using JSON Patch operations.

Update Gift Card

Tool to update gift card properties using JSON Patch operations.

Update Gift Card Settings

Tool to update gift card settings using JSON Patch operations.

Update Item

Update an item's properties using JSON Patch operations.

Update Item Group

Tool to update an item group's properties using JSON Patch operations.

Update Order

Tool to update an order's properties using JSON Patch operations.

Update Stripe Connection

Tool to update Stripe integration connection settings for the Gift Up account.

Upload Gift Card Artwork

Tool to upload new gift card artwork.

Void Gift Card

Tool to void a gift card making it invalid for future redemptions.

FAQ

Frequently asked questions

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

Yes, you can. Autogen 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 Gift up tools.

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

Start with Gift up.It takes 30 seconds.

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

Start building