How to integrate Cardly MCP with LangChain

This guide walks you through connecting Cardly to LangChain using the Composio tool router. By the end, you'll have a working Cardly agent that can create a new contact list named 'vip clients', list all available artwork for our next campaign, generate a preview of a card using latest artwork through natural language commands. This guide will help you understand how to give your LangChain 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.

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 LangChain using the Composio tool router. By the end, you'll have a working Cardly agent that can create a new contact list named 'vip clients', list all available artwork for our next campaign, generate a preview of a card using latest artwork through natural language commands.

This guide will help you understand how to give your LangChain 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.

Also integrate Cardly with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Cardly project to Composio
  • Create a Tool Router MCP session for Cardly
  • Initialize an MCP client and retrieve Cardly tools
  • Build a LangChain agent that can interact with Cardly
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

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 step10 STEPS
1

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming
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

npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • @composio/langchain provides Composio integration for LangChain
  • @langchain/mcp-adapters enables MCP client connections
  • @langchain/core is the core agent framework
  • dotenv/config loads environment variables
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_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 your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models
5

Import dependencies

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

dotenv.config();
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv/config import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Cardly functionality through MCP
6

Initialize Composio client

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

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Cardly tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding
7

Create a Tool Router session

const session = await composio.create(
    userId as string,
    {
        toolkits: ['cardly']
    }
);

const url = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Cardly tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Cardly tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "cardly-agent": {
        transport: "http",
        url: url,
        headers: {
            "x-api-key": process.env.COMPOSIO_API_KEY
        }
    }
});

const tools = await client.getTools();

const agent = createAgent({ model: "gpt-5", tools });
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Cardly MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Cardly tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model
9

Set up interactive chat interface

let conversationHistory: any[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log("Ask any Cardly related question or task to the agent.\n");

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

rl.prompt();

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

    if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
        console.log("\nGoodbye!");
        rl.close();
        process.exit(0);
    }

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

    conversationHistory.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    const response = await agent.invoke({ messages: conversationHistory });
    conversationHistory = response.messages;

    const finalResponse = response.messages[response.messages.length - 1]?.content;
    console.log(`Agent: ${finalResponse}\n`);
        
        rl.prompt();
    });

    rl.on('close', () => {
        console.log('\n👋 Session ended.');
        process.exit(0);
    });
What's happening:
  • We initialize an empty conversationHistory list to maintain context across interactions
  • A readline interface is used to continuously accept user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the invoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully
10

Run the application

main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
What's happening:
  • We call the main() function to start the application

Complete Code

Here's the complete code to get you started with Cardly and LangChain:

import { Composio } from '@composio/core';
import { LangchainProvider } from '@composio/langchain';
import { MultiServerMCPClient } from "@langchain/mcp-adapters";  
import { createAgent } from "langchain";
import * as readline from 'readline';
import 'dotenv/config';

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

if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set');
if (!userId) throw new Error('COMPOSIO_USER_ID is not set');

async function main() {
    const composio = new Composio({
        apiKey: composioApiKey as string,
        provider: new LangchainProvider()
    });

    const session = await composio.create(
        userId as string,
        {
            toolkits: ['cardly']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "cardly-agent": {
            transport: "http",
            url: url,
            headers: {
                "x-api-key": process.env.COMPOSIO_API_KEY
            }
        }
    });
    
    const tools = await client.getTools();
  
    const agent = createAgent({ model: "gpt-5", tools });
    
    let conversationHistory: any[] = [];
    
    console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
    console.log("Ask any Cardly related question or task to the agent.\n");
    
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout,
        prompt: 'You: '
    });

    rl.prompt();

    rl.on('line', async (userInput: string) => {
        const trimmedInput = userInput.trim();
        
        if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) {
            console.log("\nGoodbye!");
            rl.close();
            process.exit(0);
        }
        
        if (!trimmedInput) {
            rl.prompt();
            return;
        }
        
        conversationHistory.push({ role: "user", content: trimmedInput });
        console.log("\nAgent is thinking...\n");
        
        const response = await agent.invoke({ messages: conversationHistory });
        conversationHistory = response.messages;
        
        const finalResponse = response.messages[response.messages.length - 1]?.content;
        console.log(`Agent: ${finalResponse}\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

You've successfully built a LangChain agent that can interact with Cardly through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
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

Tool to create a new webhook subscription.

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

Tool to retrieve active invitations for your organisation with optional filters.

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

Retrieves all webhooks configured for your organization, including their status, target URLs, subscribed events, and 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

Tool to update a webhook’s settings, including target URL and events.

FRAMEWORKS

How to build Cardly MCP Agent with another framework

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

Claude Code logo

Claude Code

Use Cardly MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Cardly MCP with Claude Cowork

Codex logo

Codex

Use Cardly MCP with Codex

OpenClaw logo

OpenClaw

Use Cardly MCP with OpenClaw

Hermes logo

Hermes

Use Cardly MCP with Hermes

CLI logo

CLI

Use Cardly MCP with CLI

Google ADK logo

Google ADK

Use Cardly MCP with Google ADK

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

CrewAI logo

CrewAI

Use Cardly MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, you can. LangChain 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 Cardly tools.

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

Start with Cardly.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Cardly 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