# How to integrate Postalytics MCP with LangChain

```json
{
  "title": "How to integrate Postalytics MCP with LangChain",
  "toolkit": "Postalytics",
  "toolkit_slug": "postalytics",
  "framework": "LangChain",
  "framework_slug": "langchain",
  "url": "https://composio.dev/toolkits/postalytics/framework/langchain",
  "markdown_url": "https://composio.dev/toolkits/postalytics/framework/langchain.md",
  "updated_at": "2026-03-29T06:46:11.008Z"
}
```

## Introduction

This guide walks you through connecting Postalytics to LangChain using the Composio tool router. By the end, you'll have a working Postalytics agent that can create a new direct mail campaign, sync contacts from hubspot to postalytics, track delivery status for recent campaigns through natural language commands.
This guide will help you understand how to give your LangChain agent real control over a Postalytics account through Composio's Postalytics MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Postalytics with

- [OpenAI Agents SDK](https://composio.dev/toolkits/postalytics/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/postalytics/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/postalytics/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/postalytics/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/postalytics/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/postalytics/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/postalytics/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/postalytics/framework/cli)
- [Google ADK](https://composio.dev/toolkits/postalytics/framework/google-adk)
- [Vercel AI SDK](https://composio.dev/toolkits/postalytics/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/postalytics/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/postalytics/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/postalytics/framework/crew-ai)

## TL;DR

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

The Postalytics MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Postalytics account. It provides structured and secure access so your agent can perform Postalytics operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `POSTALYTICS_ADD_ACCOUNT` | Add Account | Tool to create a new sub-account in the Postalytics system. Use when you need to create a new account with a unique ID associated with the requester's user ID as parent. The response includes the API key and user ID for the new account, which should be stored for future API calls. |
| `POSTALYTICS_ADD_CONTACT` | Add Contact | Tool to add a contact to a specified contact list with their information. Use when you need to create a new contact or update an existing one on a contact list. |
| `POSTALYTICS_CREATE_NEW_CAMPAIGN` | Create New Campaign | Tool to create a new direct mail campaign in Postalytics. Use when you need to start a new campaign with specified sender details and template. Important: A template must be created and proofed before creating the campaign. |
| `POSTALYTICS_CREATE_SUPPRESSION_LIST` | Create Suppression List | Tool to create a new suppression list that can be used in campaigns to suppress contacts from being sent mail. Use when you need to create an empty suppression list. Note that contacts must be added separately using the SuppressionListContact API after the list is created. |
| `POSTALYTICS_CREATE_SUPPRESSION_LIST_CONTACT` | Create Suppression List Contact | Tool to create a new suppression contact on a specified suppression list. Use when you need to add a contact to a suppression list to prevent them from receiving mailings. |
| `POSTALYTICS_CREATE_TEMPLATE` | Create Template | Tool to create a new template with full HTML for postcard or letter. Use when you need to create a template by providing complete HTML markup or image URLs for front/back. The template can be used for various mail types including postcards, letters, and bifolds. |
| `POSTALYTICS_CREATE_WEBHOOK` | Create Webhook | Tool to create a new webhook to receive campaign event notifications from Postalytics. Use when you need to set up a webhook endpoint that will be notified about campaign events like sent, delivered, opened, or clicked. |
| `POSTALYTICS_DELETE_ACCOUNT` | Delete Account | Tool to delete a Postalytics account and all associated campaigns, templates, and lists. Use when you need to permanently remove a sub account or sub user account. Cannot delete parent accounts. |
| `POSTALYTICS_DELETE_CAMPAIGN` | Delete Campaign | Tool to delete a campaign from the system. Use when you need to remove a campaign that is no longer needed. |
| `POSTALYTICS_DELETE_SUPPRESSION_LIST` | Delete Suppression List | Tool to delete a specified suppression list. Use when you need to remove a suppression list that is no longer needed. |
| `POSTALYTICS_DELETE_SUPPRESSION_LIST_CONTACT` | Delete Suppression List Contact | Tool to delete a specific contact from a suppression list. Use when you need to remove a contact from a suppression list in Postalytics. |
| `POSTALYTICS_GET_ALL_CONTACT_LISTS` | Get All Contact Lists | Tool to retrieve all contact lists for an account. Use when you need to get a complete list of contact lists including their IDs, names, item counts, and creation dates. |
| `POSTALYTICS_GET_ALL_CONTACTS_ON_A_LIST` | Get All Contacts on a List | Tool to retrieve all contacts from a specified contact list with pagination support. Use when you need to get contacts from a list, with optional pagination using start offset and limit parameters. |
| `POSTALYTICS_GET_ALL_DRIP_CAMPAIGNS` | Get All Drip Campaigns | Tool to retrieve all triggered drip campaign names and endpoint IDs in the account. Use when you need to list all available drip campaigns for the authenticated user. |
| `POSTALYTICS_GET_ALL_FLOWS` | Get All Flows | Tool to retrieve all flows for the requester's account. Use when you need to list or browse available flows. |
| `POSTALYTICS_GET_ALL_WEBHOOKS` | Get All Webhooks | Tool to retrieve all webhooks configured for the authenticated account. Use when you need to view webhook configurations for campaigns. |
| `POSTALYTICS_GET_INTEGRATIONS` | Get Integrations | Tool to retrieve all Connect integrations configured for the authenticated user's account. Use when you need to view CRM or data source integrations. |
| `POSTALYTICS_GET_MY_ACCOUNT` | Get My Account | Tool to retrieve basic account information for the authenticated user. Use when you need to get account details such as contact information, address, or API key. |
| `POSTALYTICS_GET_SUPPRESSION_LIST` | Get Suppression List | Tool to get the details of a suppression list based on the id supplied. Use when you need to retrieve information about a specific suppression list. |
| `POSTALYTICS_GET_SUPPRESSION_LIST_CONTACT` | Get Suppression List Contact | Tool to retrieve a specific contact from a suppression list. Use when you need to get details about a contact on a specific suppression list by their list ID and contact ID. |
| `POSTALYTICS_GET_SUPPRESSION_LIST_CONTACTS` | Get Suppression List Contacts | Tool to get all contacts on a specified suppression list. Use when you need to retrieve contacts that are suppressed for a particular list. |
| `POSTALYTICS_GET_SUPPRESSION_LISTS` | Get Suppression Lists | Tool to retrieve all suppression lists for the authenticated user. Use when you need to view or manage suppression lists. Returns all lists or a specific list when ID is provided. |
| `POSTALYTICS_UPDATE_ACCOUNT` | Update Account | Tool to update an existing account in the Postalytics system. Use when you need to modify account information such as contact details, address, or credentials for an existing account. |
| `POSTALYTICS_UPDATE_SUPPRESSION_LIST_CONTACT` | Update Suppression List Contact | Tool to update a suppression contact on the specified suppression list. Use when you need to modify contact information for a specific contact on a suppression list. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Postalytics MCP server is an implementation of the Model Context Protocol that connects your AI agent to Postalytics. It provides structured and secure access so your agent can perform Postalytics operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

No description provided.

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

No description provided.
```python
pip install composio-langchain langchain-mcp-adapters langchain python-dotenv
```

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

### 3. Set up environment variables

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
```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
```

### 4. Import dependencies

No description provided.
```python
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()
```

```typescript
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();
```

### 5. Initialize Composio client

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 Postalytics tools
- Validating that COMPOSIO_USER_ID is also set before proceeding
```python
async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))

    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
```

```typescript
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()
    });
```

### 6. Create a Tool Router session

What's happening:
- We're creating a Tool Router session that gives your agent access to Postalytics 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 Postalytics tools as needed
```python
# Create Tool Router session for Postalytics
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['postalytics']
)

url = session.mcp.url
```

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

const url = session.mcp.url;
```

### 7. Configure the agent with the MCP URL

No description provided.
```python
client = MultiServerMCPClient({
    "postalytics-agent": {
        "transport": "streamable_http",
        "url": session.mcp.url,
        "headers": {
            "x-api-key": os.getenv("COMPOSIO_API_KEY")
        }
    }
})

tools = await client.get_tools()

agent = create_agent("gpt-5", tools)
```

```typescript
const client = new MultiServerMCPClient({
    "postalytics-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 });
```

### 8. Set up interactive chat interface

No description provided.
```python
conversation_history = []

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

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

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

    if not user_input:
        continue

    conversation_history.append({"role": "user", "content": user_input})
    print("\nAgent is thinking...\n")

    response = await agent.ainvoke({"messages": conversation_history})
    conversation_history = response['messages']
    final_response = response['messages'][-1].content
    print(f"Agent: {final_response}\n")
```

```typescript
let conversationHistory: any[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log("Ask any Postalytics 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);
    });
```

### 9. Run the application

No description provided.
```python
if __name__ == "__main__":
    asyncio.run(main())
```

```typescript
main().catch((err) => {
    console.error('Fatal error:', err);
    process.exit(1);
});
```

## Complete Code

```python
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    
    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
    
    session = composio.create(
        user_id=os.getenv("COMPOSIO_USER_ID"),
        toolkits=['postalytics']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "postalytics-agent": {
            "transport": "streamable_http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    })
    
    tools = await client.get_tools()
  
    agent = create_agent("gpt-5", tools)
    
    conversation_history = []
    
    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Ask any Postalytics related question or task to the agent.\n")
    
    while True:
        user_input = input("You: ").strip()
        
        if user_input.lower() in ['exit', 'quit', 'bye']:
            print("\nGoodbye!")
            break
        
        if not user_input:
            continue
        
        conversation_history.append({"role": "user", "content": user_input})
        print("\nAgent is thinking...\n")
        
        response = await agent.ainvoke({"messages": conversation_history})
        conversation_history = response['messages']
        final_response = response['messages'][-1].content
        print(f"Agent: {final_response}\n")

if __name__ == "__main__":
    asyncio.run(main())
```

```typescript
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: ['postalytics']
        }
    );

    const url = session.mcp.url;
    
    const client = new MultiServerMCPClient({
        "postalytics-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 Postalytics 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 Postalytics 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.

## How to build Postalytics MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/postalytics/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/postalytics/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/postalytics/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/postalytics/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/postalytics/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/postalytics/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/postalytics/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/postalytics/framework/cli)
- [Google ADK](https://composio.dev/toolkits/postalytics/framework/google-adk)
- [Vercel AI SDK](https://composio.dev/toolkits/postalytics/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/postalytics/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/postalytics/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/postalytics/framework/crew-ai)

## Related Toolkits

- [Reddit](https://composio.dev/toolkits/reddit) - Reddit is a social news platform with thriving user-driven communities (subreddits). It's the go-to place for discussion, content sharing, and viral marketing.
- [Facebook](https://composio.dev/toolkits/facebook) - Facebook is a social media and advertising platform for businesses and creators. It helps you connect, share, and manage content across your public Facebook Pages.
- [Linkedin](https://composio.dev/toolkits/linkedin) - LinkedIn is a professional networking platform for connecting, sharing content, and engaging with business opportunities. It's the go-to place for building your professional brand and unlocking new career connections.
- [Active campaign](https://composio.dev/toolkits/active_campaign) - ActiveCampaign is a marketing automation and CRM platform for managing email campaigns, sales pipelines, and customer segmentation. It helps businesses engage customers and drive growth through smart automation and targeted outreach.
- [ActiveTrail](https://composio.dev/toolkits/active_trail) - ActiveTrail is a user-friendly email marketing and automation platform. It helps you reach subscribers and automate campaigns with ease.
- [Ahrefs](https://composio.dev/toolkits/ahrefs) - Ahrefs is an SEO and marketing platform for site audits, keyword research, and competitor insights. It helps you improve search rankings and drive organic traffic.
- [Amcards](https://composio.dev/toolkits/amcards) - AMCards lets you create and mail personalized greeting cards online. Build stronger customer relationships with easy, automated card campaigns.
- [Beamer](https://composio.dev/toolkits/beamer) - Beamer is a news and changelog platform for in-app announcements and feature updates. It helps companies boost user engagement by sharing news where users are most active.
- [Benchmark email](https://composio.dev/toolkits/benchmark_email) - Benchmark Email is a platform for creating, sending, and tracking email campaigns. It's built to help you engage audiences and analyze results—all in one place.
- [Bigmailer](https://composio.dev/toolkits/bigmailer) - BigMailer is an email marketing platform for managing multiple brands with white-labeling and automation. It helps teams streamline campaigns and simplify integration with Amazon SES.
- [Brandfetch](https://composio.dev/toolkits/brandfetch) - Brandfetch is an API that delivers company logos, colors, and visual branding assets. It helps marketers and developers keep brand visuals consistent everywhere.
- [Brevo](https://composio.dev/toolkits/brevo) - Brevo is an all-in-one email and SMS marketing platform for transactional messaging, automation, and CRM. It helps businesses engage customers and streamline communications through powerful campaign tools.
- [Campayn](https://composio.dev/toolkits/campayn) - Campayn is an email marketing platform for creating, sending, and managing campaigns. It helps businesses engage contacts and grow audiences with easy-to-use tools.
- [Cardly](https://composio.dev/toolkits/cardly) - 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.
- [ClickSend](https://composio.dev/toolkits/clicksend) - ClickSend is a cloud-based SMS and email marketing platform for businesses. It streamlines communication by enabling quick message delivery and contact management.
- [Crustdata](https://composio.dev/toolkits/crustdata) - CrustData is an AI-powered data intelligence platform for real-time company and people data. It helps B2B sales teams, AI SDRs, and investors react to live business signals.
- [Curated](https://composio.dev/toolkits/curated) - Curated is a platform for collecting, curating, and publishing newsletters. It streamlines content aggregation and distribution for creators and teams.
- [Customerio](https://composio.dev/toolkits/customerio) - Customer.io is a customer engagement platform for targeted messaging across email, SMS, and push. Easily automate, segment, and track communications with your audience.
- [Cutt ly](https://composio.dev/toolkits/cutt_ly) - Cutt.ly is a URL shortening service for managing and analyzing links. Streamline your workflows with quick, trackable, and branded short URLs.
- [Demio](https://composio.dev/toolkits/demio) - Demio is webinar software built for marketers, offering both live and automated sessions with interactive features. It helps teams engage audiences and optimize lead generation through detailed analytics.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Postalytics MCP?

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

### Can I use Tool Router MCP with LangChain?

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 Postalytics tools.

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

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

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
