SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Stannp MCP with LangChain

Connect LangChain to Stannp MCP. Add new customer to holiday postcard group, import client mailing list from spreadsheet, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Stannp logoStannp
Api Key

Stannp is an API-driven direct mail platform for sending postcards and letters programmatically. It lets you automate physical mail delivery—no manual printing or mailing required.

32 Tools

Introduction

This guide walks you through connecting Stannp to LangChain using the Composio tool router. By the end, you'll have a working Stannp agent that can send postcards and letters, create mail campaigns, manage recipient groups, validate addresses, and check your account balance through natural language commands.

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

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

Also integrate Stannp with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Stannp project to Composio
  • Create a Tool Router MCP session for Stannp
  • Initialize an MCP client and retrieve Stannp tools
  • Build a LangChain agent that can interact with Stannp
  • 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 Stannp MCP server, and what's possible with it?

The Stannp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Stannp account. It provides structured and secure access to your direct mail contacts, groups, and templates, so your agent can perform actions like managing recipient lists, importing contacts, and retrieving mailing templates on your behalf.

  • Organize and manage recipient groups: Easily create new recipient groups and add contacts, helping you segment your mailing lists for targeted direct mail campaigns.
  • Import bulk recipients efficiently: Let your agent upload and import contacts from CSV or XLS files directly into Stannp, streamlining the process of building large mailing lists.
  • Retrieve and view contact details: Instantly fetch information on specific contacts or list all your contacts, making it simple to keep track of who’s in your database.
  • Access and manage templates: Quickly list and review all available Stannp templates, so your agent can select the right one when setting up new campaigns or mailings.

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 Stannp 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 Stannp 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: ['stannp']
    }
);

const url = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Stannp 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 Stannp tools as needed
8

Configure the agent with the MCP URL

const client = new MultiServerMCPClient({
    "stannp-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 Stannp MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • getTools() retrieves all available Stannp 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 Stannp 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 Stannp 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: ['stannp']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "stannp-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 Stannp 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 Stannp 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 Stannp action and event your agent gets out of the box.

Add recipients to group

Tool to add existing recipients to a mailing list group.

Add Recipient to Group

Tool to add a recipient to a recipient group.

Cancel Postcard

Tool to cancel a postcard if processing has not started yet.

Create Campaign

Tool to create a new direct mail campaign on the platform.

Create campaign sample

Tool to produce a PDF sample of your campaign.

Create folder

Tool to create a folder in your secure file transfer area.

Create recipient group

Tool to create a new recipient group in Stannp.

Create Letter

Tool to create a letter with mail merge to insert address and variable data.

Create Postcard

Create a postcard for direct mail.

Create recipient selection

Tool to create a new recipient selection for targeting in Stannp.

Delete recipient group

Tool to delete a recipient group in Stannp.

Delete Recipient

Tool to permanently delete a recipient from your account.

Get Account Balance

Tool to retrieve the current account balance.

Get Campaign

Tool to retrieve details of a specific campaign.

Get Campaign Available Dates

Tool to get available dates for scheduling a campaign (up to 30 days).

Get Campaign Cost

Tool to get the estimated cost of booking a campaign.

Get Contact

Retrieve details of a specific contact by ID, returning the contact fields supported by the response model.

Get Current User

Retrieve account details for the currently authenticated user.

Get Reporting Summary

Tool to get a status summary on individual items within a date range.

Import Recipients

Tool to import recipients from a CSV or XLS file into a Stannp recipient group.

List Campaigns

Tool to get a list of all campaigns.

List Contacts

Tool to list all contacts.

List Folders

Tool to get a list of folders in your secure file transfer area.

List Mailing Groups

Tool to get a list of mailing groups on your account.

List Mailpieces

Retrieve mailpiece objects sent within a date range to review mailing history.

List Templates

Tool to list all templates associated with the account.

Merge PDF files

Merge two or more PDF files accessible by URL into a single file, returning the merged file URL.

Purge Group

Tool to remove all recipients from a mailing list.

Recalculate group

Tool to recalculate a group to ensure stats are up to date.

Remove Recipients from Group

Tool to remove recipients from a group without deleting them.

Upload File

Tool to upload a file to your secure file transfer area.

Validate Address

Tool to validate a postal address.

FRAMEWORKS

How to build Stannp MCP Agent with another framework

Claude Code logo

Claude Code

Use Stannp MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Stannp MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Stannp MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Stannp MCP with Claude Agent SDK

Codex logo

Codex

Use Stannp MCP with Codex

OpenClaw logo

OpenClaw

Use Stannp MCP with OpenClaw

Hermes logo

Hermes

Use Stannp MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Stannp MCP with Atomic Agent

Google ADK logo

Google ADK

Use Stannp MCP with Google ADK

Vercel AI SDK logo

Vercel AI SDK

Use Stannp MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Stannp MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Stannp MCP with LlamaIndex

CrewAI logo

CrewAI

Use Stannp MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Stannp MCP with Pydantic AI

AutoGen logo

AutoGen

Use Stannp MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Stannp.It takes 30 seconds.

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

Start building