How to integrate Givebutter MCP with OpenAI Agents SDK

This guide walks you through connecting Givebutter to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Givebutter agent that can create a new fundraising campaign for our school, list all recent payouts to our nonprofit account, get details for fund with id fund_abc123 through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Givebutter account through Composio's Givebutter MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Givebutter logoGivebutter
Api Key

Givebutter is a fundraising platform with a free, open API for managing campaigns and donations. It helps organizations easily track giving, engage supporters, and streamline fundraising efforts.

58 Tools

Introduction

This guide walks you through connecting Givebutter to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Givebutter agent that can create a new fundraising campaign for our school, list all recent payouts to our nonprofit account, get details for fund with id fund_abc123 through natural language commands.

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

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

Also integrate Givebutter with

Claude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

What is OpenAI 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 Givebutter MCP server, and what's possible with it?

The Givebutter MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Givebutter account. It provides structured and secure access to your fundraising platform, so your agent can perform actions like creating campaigns, tracking donations, managing contacts, and handling payouts on your behalf.

  • Campaign management and creation: Easily instruct your agent to start new fundraising campaigns, update campaign details, or remove old campaigns when needed.
  • Donation and payout tracking: Ask your agent to retrieve lists of payouts, monitor donation flows, and keep tabs on your fundraising progress in real time.
  • Contact and member administration: Let your agent add, archive, or delete contacts, and fetch lists of campaign members for smooth supporter management.
  • Fund and webhook operations: Direct your agent to get details about specific funds, create or remove webhooks for event notifications, and manage fundraising infrastructure automatically.
  • Automated data cleanup: Empower your agent to archive or delete obsolete contacts, funds, or webhooks, keeping your Givebutter account organized and up to date.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Givebutter project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

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.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
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 Givebutter.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Givebutter
const session = await composio.create(userId as string, {
  toolkits: ['givebutter'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only givebutter.
  • The router checks the user's Givebutter connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Givebutter.
  • This approach keeps things lightweight and lets the agent request Givebutter tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Givebutter. Help users perform Givebutter operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: '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 Givebutter 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 object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Givebutter operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Givebutter.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Givebutter and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['givebutter'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Givebutter. Help users perform Givebutter operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

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

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.
TOOLS

Supported Tools

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

Add Contact Tags

Tool to add tags to a contact by contact ID.

Add Household Contact

Tool to add a contact to a household.

Archive Contact

Tool to archive a contact by their ID.

Create Campaign

Tool to create a new campaign.

Create Campaign Ticket

Tool to create a campaign ticket for events or fundraisers.

Create Contact

Tool to create a new contact in Givebutter.

Create Contact Activity

Tool to create a contact activity (e.

Create Discount Code

Tool to create a discount code for a campaign.

Create Fund

Tool to create a new fund.

Create Household

Tool to create a new household in Givebutter.

Create Transaction

Tool to create a new transaction for a campaign.

Create Webhook

Tool to create a new webhook subscription.

Delete Campaign

Tool to delete a campaign by its ID.

Delete Contact Activity

Tool to delete a contact activity by contact ID and activity ID.

Delete Discount Code

Tool to delete a discount code from a campaign.

Delete Fund

Tool to delete a fund by its ID.

Delete Household

Tool to delete a household by its ID.

Delete Webhook

Tool to delete a webhook by its ID.

Get Campaign

Tool to retrieve details for a specific campaign by its ID or code.

Get Campaign Ticket

Tool to retrieve a specific campaign ticket by campaign ID and ticket ID.

Get Contact

Tool to retrieve details of a specific contact by ID.

Get Contact Activity

Tool to retrieve a specific contact activity by contact ID and activity ID.

Get Discount Code

Tool to retrieve details of a specific discount code for a campaign.

Get Fund

Tool to retrieve details of a specific fund by its ID.

Get Household

Tool to retrieve details of a specific household by its ID.

Get Members

Tool to retrieve a paginated list of members for a given campaign.

Get Payouts

Tool to retrieve a list of payouts associated with your account.

Get Plans

Tool to retrieve a list of plans associated with your account.

Get Teams

Tool to retrieve a list of teams for a specific campaign.

Get Tickets

Tool to retrieve a list of tickets.

Get Transactions

Tool to retrieve a list of transactions associated with your account.

Get Webhook

Tool to retrieve a specific webhook by its ID.

Get Webhook Activity

Tool to retrieve a specific webhook activity by its ID.

Get Webhooks

Tool to retrieve all webhooks configured for your account.

List Campaigns

Tool to retrieve a paginated list of campaigns for the authenticated account.

List Campaign Tickets

Tool to retrieve a list of all campaign tickets for a specific campaign.

List Contact Activities

Tool to retrieve all activities for a specific contact.

List Contacts

Tool to retrieve a paginated list of contacts from your Givebutter account.

List Discount Codes

Tool to list all discount codes for a campaign.

List Funds

Tool to list all funds in your Givebutter account.

List Household Contacts

Tool to retrieve all contacts associated with a household.

List Households

Tool to retrieve a list of all households in your account.

List Messages

Tool to retrieve a paginated list of messages.

List Pledges

Tool to retrieve a paginated list of all pledges.

List Webhook Activities

Tool to list all webhook activities for a specific webhook.

Remove Contact Tags

Tool to remove tags from a contact in Givebutter.

Restore Contact

Tool to restore a deleted contact by contact ID.

Sync Contact Tags

Tool to sync tags for a contact.

Update Campaign

Tool to update an existing campaign's details by its ID.

Update Campaign (PUT)

Tool to update a campaign using PUT method.

Update Contact

Tool to update an existing contact's details by contact ID.

Update Contact Activity

Tool to update a contact activity by contact ID and activity ID.

Update Contact (PUT)

Tool to update a contact using PUT method.

Update Discount Code

Tool to update an existing discount code for a campaign.

Update Fund

Tool to update a fund's details by its ID.

Update Household

Tool to update an existing household's details by its ID.

Update Webhook

Tool to update an existing webhook subscription's details.

Update Webhook (PUT)

Tool to update a webhook using PUT method (full replacement).

FRAMEWORKS

How to build Givebutter MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Givebutter MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Givebutter MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Givebutter MCP with Claude Cowork

Codex logo

Codex

Use Givebutter MCP with Codex

OpenClaw logo

OpenClaw

Use Givebutter MCP with OpenClaw

Hermes logo

Hermes

Use Givebutter MCP with Hermes

CLI logo

CLI

Use Givebutter MCP with CLI

Google ADK logo

Google ADK

Use Givebutter MCP with Google ADK

LangChain logo

LangChain

Use Givebutter MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Givebutter MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Givebutter MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Givebutter MCP with LlamaIndex

CrewAI logo

CrewAI

Use Givebutter MCP with CrewAI

FAQ

Frequently asked questions

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

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 Givebutter tools.

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

Start with Givebutter.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies