How to integrate Resend MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Resend logo
OpenAI Agents SDK logo
divider

Introduction

This guide walks you through connecting Resend to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Resend agent that can create a new contact for your newsletter, list all domains connected to your account, cancel a scheduled marketing email through natural language commands.

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

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

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

The Resend MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Resend account. It provides structured and secure access to your email sending and contact management capabilities, so your agent can perform actions like sending emails, managing audiences, creating domains, and handling contacts on your behalf.

  • Automated email delivery and scheduling: Ask your agent to send emails instantly or schedule them for later, and even cancel scheduled messages if needed.
  • Audience and contact management: Let your agent create, list, or delete audiences and individual contacts, keeping your recipient lists organized without manual effort.
  • Domain administration: Easily have your agent set up, list, or remove email sending domains, streamlining onboarding or maintenance for your email infrastructure.
  • Seamless recipient segmentation: Direct your agent to group contacts into audiences for targeted campaigns or communications, improving personalization and reach.
  • Bulk operations and cleanups: Enable your agent to quickly list, update, or delete multiple contacts, audiences, or domains to maintain a tidy and up-to-date email system.

Supported Tools & Triggers

Tools
Add Contact To SegmentAdd an existing contact to a segment in Resend.
Cancel EmailCancel a scheduled email.
Create API KeyCreate a new API key to authenticate communications with Resend.
Create AudienceCreate a list of contacts.
Create ContactCreate a contact in Resend.
Create Contact PropertyTool to create a new contact property in Resend.
Create Contact V2Tool to create a new contact in Resend.
Create DomainCreate a domain through the Resend Email API.
Create TemplateTool to create a new email template in Resend.
Create TopicTool to create a new topic to segment your audience.
Create WebhookTool to create a webhook to receive real-time notifications about email events.
Delete API KeyRemove an existing API key from Resend.
Delete AudienceRemove an existing audience.
Delete ContactDelete a contact in Resend.
Delete Contact By IDTool to remove an existing contact by its ID.
Delete Contact PropertyRemove an existing contact property from Resend.
Delete DomainDelete a domain through the Resend Email API.
Delete SegmentRemove an existing segment.
Delete TemplateRemove an existing template.
Delete TopicTool to remove an existing topic in Resend.
Delete WebhookRemove an existing webhook.
Duplicate TemplateDuplicate an existing template through the Resend Email API.
Get ContactTool to retrieve a single contact from Resend by ID or email.
Get Contact PropertyTool to retrieve a single contact property from Resend.
Get Email AttachmentRetrieve a single attachment from a sent email.
Get SegmentRetrieve a single segment by its ID.
Get TemplateRetrieve a single template by ID or alias from Resend.
Get TopicTool to retrieve a single topic by its ID in Resend.
Get WebhookRetrieve a single webhook for the authenticated user.
List All ContactsTool to retrieve a list of all contacts from Resend.
List API KeysTool to retrieve a list of API keys for the authenticated user.
List AudiencesList all audiences.
List BroadcastsTool to retrieve a list of broadcasts.
List Contact PropertiesTool to retrieve a list of contact properties from Resend.
List ContactsList contacts in Resend.
List Contact SegmentsRetrieve a list of segments that a contact is part of.
List Contact TopicsRetrieve a list of topic subscriptions for a contact in Resend.
List DomainsList all domains.
List Email AttachmentsTool to retrieve a list of attachments from a sent email.
List EmailsTool to retrieve a list of emails sent by your team.
List Received EmailsTool to retrieve a list of received emails for the authenticated user.
List SegmentsTool to retrieve a list of segments from Resend.
List TemplatesTool to retrieve a list of templates from Resend.
List TopicsTool to retrieve a list of topics for the authenticated user.
List WebhooksRetrieve a list of webhooks for the authenticated user.
Publish TemplatePublish a template through the Resend Email API.
Remove Contact From SegmentRemove an existing contact from a segment.
Retrieve AudienceRetrieve a single audience.
Retrieve ContactRetrieve a contact in Resend.
Retrieve DomainRetrieve a single domain.
Retrieve EmailRetrieve a single email.
Send Batch EmailsTrigger up to 100 batch emails at once.
Send EmailSend an email using Resend.
Update BroadcastUpdate an existing broadcast in Resend.
Update ContactTool to update an existing contact in Resend by ID or email.
Update Contact PropertyUpdate an existing contact property in Resend.
Update DomainUpdate an existing domain.
Update EmailUpdate a scheduled email.
Update TemplateTool to update an existing email template in Resend.
Update TopicTool to update an existing topic in Resend.
Update WebhookTool to update an existing webhook configuration.
Verify DomainVerify a domain through the Resend Email API.

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 Resend 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 Resend.

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 Resend Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["resend"]
)

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

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 Resend MCP Agent with another framework

FAQ

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

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

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

Yes, absolutely. You can configure which Resend 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 Resend 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.