How to integrate Lettr MCP with CrewAI

This guide walks you through connecting Lettr to CrewAI using the Composio tool router. By the end, you'll have a working Lettr agent that can create email templates, add your contacts, create audience segments, create your lists, and set up webhooks through natural language commands. This guide will help you understand how to give your CrewAI agent real control over a Lettr account through Composio's Lettr 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
Lettr logoLettr
Api Key

Lettr is an email and messaging platform for transactional delivery, templates, audiences, campaigns, domains, and webhooks. Use it to send reliable product emails and manage customer messaging from one place.

60 Tools

Introduction

This guide walks you through connecting Lettr to CrewAI using the Composio tool router. By the end, you'll have a working Lettr agent that can create email templates, add your contacts, create audience segments, create your lists, and set up webhooks through natural language commands.

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

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

Also integrate Lettr with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndex

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Lettr connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Lettr
  • Build a conversational loop where your agent can execute Lettr operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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

The Lettr MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Lettr account. It provides structured and secure access to your audiences, templates, campaigns, sending domains, webhooks, and email delivery records, so your agent can organize contacts, create templates, configure sending resources, monitor campaigns, and track emails on your behalf.

  • Audience and contact management: Have your agent create, find, and delete contacts, organize them into lists, and manage their list memberships.
  • Segments, properties, and topics: Let the agent define contact properties, build dynamic audience segments, and manage public or private subscription topics.
  • Email template management: Direct your agent to create and publish HTML or editor-based templates, inspect required merge tags, retrieve template content, or remove old templates.
  • Campaign and delivery monitoring: Instruct your agent to review campaigns, delivery and engagement statistics, campaign events, sent email status, and scheduled email activity, or cancel an email before processing begins.
  • Domains and webhook configuration: Have your agent register sending domains, check DNS and verification status, and create or remove event webhooks with supported authentication settings.

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

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Lettr connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python
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 crewai crewai-tools[mcp] python-dotenv
What's happening:
  • composio connects your agent to Lettr via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools[mcp] includes MCP helpers
  • python-dotenv loads environment variables from .env
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model
5

Import dependencies

python
import os
from composio import Composio
from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
import dotenv

dotenv.load_dotenv()

COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Lettr MCP URL
6

Create a Composio Tool Router session for Lettr

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["lettr"])

url = session.mcp.url
What's happening:
  • You create a Lettr only session through Composio
  • Composio returns an MCP HTTP URL that exposes Lettr tools
7

Initialize the MCP Server

python
server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users search the internet effectively",
        backstory="You are a helpful assistant with access to search tools.",
        tools=tools,
        verbose=False,
        max_iter=10,
    )
What's Happening:
  • Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication.
  • MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format.
  • Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools.
  • Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops.
  • Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries.
8

Create a CLI Chatloop and define the Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")

conversation_context = ""

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

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

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Conversation history:\n{conversation_context}\n\n"
            f"Current request: {user_input}"
        ),
        expected_output="A helpful response addressing the user's request",
        agent=agent,
    )

    crew = Crew(agents=[agent], tasks=[task], verbose=False)
    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's Happening:
  • Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable.
  • Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean.
  • Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses.
  • Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context.
  • Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response.
  • Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity.

Complete Code

Here's the complete code to get you started with Lettr and CrewAI:

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter
from composio import Composio
from dotenv import load_dotenv
import os

load_dotenv()

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

# Initialize Composio and create a session
composio = Composio(api_key=COMPOSIO_API_KEY)
session = composio.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["lettr"],
)
url = session.mcp.url

# Configure LLM
llm = LLM(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY"),
)

server_params = {
    "url": url,
    "transport": "streamable-http",
    "headers": {"x-api-key": COMPOSIO_API_KEY},
}

with MCPServerAdapter(server_params) as tools:
    agent = Agent(
        role="Search Assistant",
        goal="Help users with internet searches",
        backstory="You are an expert assistant with access to Composio Search tools.",
        tools=tools,
        llm=llm,
        verbose=False,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end.\n")

    conversation_context = ""

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

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

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Conversation history:\n{conversation_context}\n\n"
                f"Current request: {user_input}"
            ),
            expected_output="A helpful response addressing the user's request",
            agent=agent,
        )

        crew = Crew(agents=[agent], tasks=[task], verbose=False)
        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

Conclusion

You now have a CrewAI agent connected to Lettr through Composio's Tool Router. The agent can perform Lettr operations through natural language commands.

Next steps:

  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations
TOOLS

Supported Tools

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

Attach Contacts to Lists

Attach every combination of 1-1000 contacts and 1-50 audience lists, processing up to 50,000 contact-list pairs and reporting new and existing memberships.

Bulk Create Audience Contacts

Create or recognize up to 1000 normalized, deduplicated contacts.

Cancel Scheduled Email

Cancel a scheduled email before its delivery time; cancellation is unavailable once processing has begun.

Create Audience Contact

Create one audience contact with optional properties and list membership.

Create Audience Contact With Double Opt-In

Create an unverified audience contact and irreversibly send an external confirmation email; the contact becomes subscribed only after confirming.

Create Audience List

Create a uniquely named audience list for grouping contacts.

Create Audience Property

Define a custom contact property with an immutable name and value type.

Create Audience Segment

Create a dynamic audience segment whose condition groups are ANDed while conditions inside each group are ORed.

Create Audience Topic

Create a public or private subscription topic with an immutable opt-in or opt-out default.

Create Domain

Register a sending domain and return the DNS configuration needed to verify it.

Create Template

Create and publish an email template from either custom HTML or Topol editor JSON, extracting its merge tags.

Create Webhook

Create an active event webhook using no authentication, HTTP Basic credentials, or OAuth 2 client credentials.

Delete Audience Contact

Permanently delete one audience contact and its associated memberships.

Delete Audience Lists

Permanently delete between 1 and 50 audience lists in one request.

Delete Audience Property

Permanently delete a custom contact-property definition.

Delete Audience Segment

Permanently delete one dynamic audience segment.

Delete Audience Topic

Permanently delete one audience subscription topic.

Delete Domain

Permanently remove a sending domain from Lettr and SparkPost so it can no longer send email.

Delete Template

Permanently delete an email template and all of its versions.

Delete Webhook

Permanently remove a webhook so Lettr stops delivering events to it.

Detach Contacts from Lists

Detach every combination of 1-1000 contacts and 1-50 audience lists, reporting removed and absent memberships.

Get Audience Contact

Retrieve one contact's email, status, custom properties, list memberships, and topic subscriptions by ID.

Get Audience List

Retrieve one audience list and its current contact count by ID.

Get Audience Property

Retrieve one custom contact-property definition and its fallback value.

Get Audience Segment

Retrieve one dynamic segment's list restriction, complete AND-of-OR condition definition, and cached contact count.

Get Audience Topic

Retrieve one subscription topic's defaults, visibility, and current contact count.

Get Campaign

Retrieve one campaign's name, subject, sender and reply-to configuration, schedule, rendered HTML, lifecycle state, recipient counts, and engagement statistics.

Get Domain

Retrieve one sending domain's send readiness, DNS records, provider detection, and verification status.

Get Email

Retrieve a sent email's delivery state, recipients, schedule metadata, and events by request ID.

Get Scheduled Email

Retrieve a scheduled email's current state and events by transmission ID, including after it has been processed.

Get Template

Retrieve an email template's metadata, active HTML or editor JSON content, and version counts by slug.

Get Template Merge Tags

Return required and optional merge tags for a template's active or specified version before sending with substitution data.

Get Webhook

Retrieve one webhook's target, enabled state, event selection, authentication mode, and latest delivery status.

List Audience Contacts

Return one cursor-controlled page of contacts, optionally filtered by search text, status, list, or segment.

List Audience Lists

Return one cursor-controlled page of audience lists with each list's contact count.

List Audience Properties

Return one cursor-controlled page of custom contact-property definitions and fallback values.

List Audience Segments

Return one cursor-controlled page of dynamic audience segments, including their complete AND-of-OR condition definitions, optionally filtered by list.

List Audience Topics

Return one cursor-controlled page of subscription topics with defaults, visibility, and contact counts.

List Campaign Events

Return one cursor-controlled page of a campaign's delivery and engagement events, with event, recipient, and time filters.

List Campaigns

Return one cursor-controlled page of campaigns with complete delivery and engagement statistics, optionally filtered by lifecycle status.

List Domains

Return all sending domains with approval, DNS verification, and send-readiness status.

List Email Events

Return one cursor-controlled page of delivery and engagement events across sent emails, with event, recipient, transmission, bounce, and date filters.

List Sent Emails

Return one cursor-controlled page of sent emails, optionally filtered by recipient and date range.

List Projects

Return one cursor-controlled page of Lettr projects and their IDs for use with template operations.

List Templates

Return one cursor-controlled page of email templates for a project or the team's default project.

List Webhooks

Return all event webhooks with target, enabled state, event selection, authentication mode, and latest delivery status.

Publish Template Version

Create and activate a new version of an existing email template from exactly one of HTML or Topol editor JSON, optionally renaming the template atomically.

Schedule Campaign

Schedule a campaign for future delivery or reschedule it.

Schedule Email

Create a transactional email scheduled 5 minutes to 3 days in the future; it remains cancellable until processed.

Send Campaign

Immediately and irreversibly start sending a sendable draft campaign to its resolved audience.

Send Email

Immediately queue a transactional email to up to 50 recipients using inline content or a Lettr template.

Unschedule Campaign

Cancel a scheduled campaign send and return the campaign to draft.

Update Audience Contact

Change a contact's email, subscribed or unsubscribed status, or selected custom property values.

Update Audience List

Rename an audience list while preserving its contacts.

Update Audience Property

Set or clear a custom contact property's fallback value.

Update Audience Segment

Change a dynamic segment's name, optional audience-list restriction, or complete AND-of-OR condition definition.

Update Audience Topic

Change a subscription topic's name, description, or public/private visibility.

Update Template

Rename an email template's metadata without publishing a new version.

Update Webhook

Partially update a webhook's name, callback URL, authentication, selected events, or active state.

Verify Domain

Run Lettr's DNS verification for a registered domain and return DKIM, CNAME, DMARC, SPF, and ownership results.

FRAMEWORKS

How to build Lettr MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Lettr MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Lettr MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Lettr MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Lettr MCP with Claude Cowork

Codex logo

Codex

Use Lettr MCP with Codex

OpenClaw logo

OpenClaw

Use Lettr MCP with OpenClaw

Hermes logo

Hermes

Use Lettr MCP with Hermes

CLI logo

CLI

Use Lettr MCP with CLI

Google ADK logo

Google ADK

Use Lettr MCP with Google ADK

LangChain logo

LangChain

Use Lettr MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Lettr MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Lettr MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Lettr MCP with LlamaIndex

FAQ

Frequently asked questions

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

Yes, you can. CrewAI 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 Lettr tools.

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

Start with Lettr.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Lettr 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