SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Cardly MCP with CrewAI

Connect CrewAI to Cardly MCP. Create a new contact list named 'vip clients', list all available artwork for our next campaign, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Cardly logoCardly
Api Key

Cardly is a platform for creating and sending personalized direct mail to customers. It helps businesses break through the digital clutter by getting real engagement via physical mailboxes.

29 Tools

Introduction

This guide walks you through connecting Cardly to CrewAI using the Composio tool router. By the end, you'll have a working Cardly agent that can preview personalized cards, browse artwork and templates, track orders, manage contact lists, and check your account balance through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Cardly with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexPydantic AIAutoGen

TL;DR

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

The Cardly MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cardly account. It provides structured and secure access to your Cardly workspace, so your agent can create contact lists, generate card previews, manage invitations, and access artwork or credit history for seamless customer engagement tasks.

  • Automated contact list creation and management: Easily instruct your agent to set up new contact lists or manage existing ones, streamlining outreach campaigns and personalized mailings.
  • Card preview generation and artwork browsing: Let your agent generate watermarked card previews and browse available artwork to help you select the right designs before sending mailers.
  • Real-time credit and gift history access: Ask your agent to fetch your credit or gift credit history so you always know your account status and can track usage or plan new campaigns.
  • Invitation and webhook management: Direct your agent to handle invitations—listing, deleting, or auditing user invites—or manage webhooks for seamless integration with other systems.
  • Font and design asset exploration: Have your agent list available fonts and artwork, making it easier to choose creative assets for your next customer engagement initiative.

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 Cardly 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 Cardly 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 Cardly MCP URL
6

Create a Composio Tool Router session for Cardly

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

url = session.mcp.url
What's happening:
  • You create a Cardly only session through Composio
  • Composio returns an MCP HTTP URL that exposes Cardly 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 Cardly 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=["cardly"],
)
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 Cardly through Composio's Tool Router. The agent can perform Cardly 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 Cardly action and event your agent gets out of the box.

Create Contact List

Tool to add a new contact list.

Create Invitation

Tool to send an invitation to use your organisation portal.

Create Webhook

Creates a Cardly webhook subscription to send HTTP POST notifications to a specified HTTPS endpoint when subscribed events occur.

Delete Invitation

Tool to delete an invitation by unique ID, immediately invalidating it for acceptance.

Delete Invitation by Email

Deletes a pending invitation by email address, immediately invalidating it and preventing acceptance.

Delete User

Tool to delete a user by unique ID, immediately revoking their access to your organisation portal.

Delete User by Email

Deletes a user by email address, immediately revoking their access to your organisation portal.

Delete Webhook

Tool to delete a webhook.

Echo Request

Tool to echo all request parameters, body, and headers for debugging purposes.

Generate Preview

Tool to generate a low-quality, watermarked preview document for a card.

Get Artwork

Tool to retrieve information on a specific piece of artwork by its unique ID.

Get Webhook

Tool to get details on an existing webhook.

List Artwork

Tool to retrieve the currently available artwork for your organisation.

List Contact Lists

Tool to retrieve all active contact lists for your organization.

List Credit History

Retrieves the account's credit transaction history showing all credits and debits.

List Doodles

Retrieve your currently available doodles from Cardly.

List Fonts

List available fonts for handwriting and text personalization in Cardly cards.

List Gift Credit History

Lists gift credit history records for your organization with pagination and optional time-based filtering.

List Invitations

Retrieve invitations for your organisation with optional status filters and pagination.

List Media

Tool to retrieve the currently available media sizes for product artwork.

List Orders

Retrieves a paginated list of orders placed by your organization.

List Templates

Tool to retrieve your currently available templates from Cardly.

List Users

Tool to retrieve all users associated with your account.

List Webhooks

Lists webhooks configured for your organization in pages, including their status, target URLs, subscribed events, and available delivery statistics.

List Writing Styles

Tool to list available writing styles.

Retrieve Account Balance

Tool to retrieve the current account and gift credit balances for your organisation.

Retrieve Order

Retrieves detailed information about a specific order by its ID.

Retrieve User

Retrieves detailed information about a specific user account by ID.

Update Webhook

Updates a webhook’s settings by ID, including its target URL and subscribed events.

FRAMEWORKS

How to build Cardly MCP Agent with another framework

Claude Code logo

Claude Code

Use Cardly MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Cardly MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Cardly MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Cardly MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Cardly MCP with Grok Bot

Codex logo

Codex

Use Cardly MCP with Codex

OpenClaw logo

OpenClaw

Use Cardly MCP with OpenClaw

Hermes logo

Hermes

Use Cardly MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Cardly MCP with Atomic Agent

Google ADK logo

Google ADK

Use Cardly MCP with Google ADK

LangChain logo

LangChain

Use Cardly MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Cardly MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Cardly MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Cardly MCP with LlamaIndex

Pydantic AI logo

Pydantic AI

Use Cardly MCP with Pydantic AI

AutoGen logo

AutoGen

Use Cardly MCP with AutoGen

FAQ

Frequently asked questions

Start with Cardly.It takes 30 seconds.

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

Start building