How to integrate Postgrid MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Postgrid Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Postgrid to CrewAI using the Composio tool router. By the end, you'll have a working Postgrid agent that can send a letter to new customer address, verify and standardize a shipping address, create a reusable postcard template, delete outdated contact from mailing list through natural language commands.

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

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

TL;DR

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

The Postgrid MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Postgrid account. It provides structured and secure access to your direct mail and address automation tools, so your agent can verify addresses, send letters, manage contacts, and handle templates for your business communications—all without manual intervention.

  • Automated letter sending: Have your agent create and send physical letters on demand, handling recipient, sender, and content details seamlessly.
  • Contact management: Effortlessly add, update, or delete contacts in your Postgrid account to keep your mailing lists accurate and up to date.
  • Template creation and maintenance: Let your agent generate reusable mail templates with dynamic placeholders, and remove outdated templates as needed.
  • Bank account and payment management: Create or delete bank accounts associated with print and mail services, ensuring smooth financial operations for mail automation.
  • Webhook setup and monitoring: Enable your agent to create or remove webhooks to track events and receive real-time notifications for your mail orders and services.

Supported Tools & Triggers

Tools
CREATE_BANK_ACCOUNTTool to create a new bank account for print & mail service.
Create ContactTool to create a new contact in postgrid.
Create LetterTool to create and send a letter via postgrid.
Create TemplateTool to create a new mail template in postgrid.
Create WebhookTool to create a new webhook to receive order event notifications.
Delete Bank AccountTool to delete a bank account by its id.
Delete ContactTool to delete a contact by its id.
Delete TemplateTool to delete a template by its id.
Delete WebhookTool to delete a webhook subscription.
Get Bank AccountTool to retrieve a bank account.
Get ContactTool to retrieve a contact.
Get LetterTool to retrieve a letter.
Get TemplateTool to retrieve a template.
Get WebhookTool to retrieve details of a specific webhook by its id.
List Bank AccountsTool to list bank accounts.
List ChequesTool to list cheques with optional filters and pagination.
List ContactsTool to list contacts.
List LettersTool to list letters.
List PostcardsTool to retrieve a list of postcards with optional filtering and pagination.
List Self-MailersTool to list self-mailers.
List TemplatesTool to list templates.
List WebhooksTool to retrieve a list of configured webhooks with optional filtering and pagination.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Postgrid connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Postgrid via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

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

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
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 Postgrid MCP URL

Create a Composio Tool Router session for Postgrid

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["postgrid"],
)
url = session.mcp.url
What's happening:
  • You create a Postgrid only session through Composio
  • Composio returns an MCP HTTP URL that exposes Postgrid tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Postgrid Assistant",
    goal="Help users interact with Postgrid through natural language commands",
    backstory=(
        "You are an expert assistant with access to Postgrid tools. "
        "You can perform various Postgrid operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Postgrid MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Postgrid operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Postgrid related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_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:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_postgrid_agent.py

Complete Code

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

python
# file: crewai_postgrid_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Postgrid session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["postgrid"],
    )
    url = session.mcp.url

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

    # Create Postgrid assistant agent
    toolkit_agent = Agent(
        role="Postgrid Assistant",
        goal="Help users interact with Postgrid through natural language commands",
        backstory=(
            "You are an expert assistant with access to Postgrid tools. "
            "You can perform various Postgrid operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Postgrid operations.\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"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Postgrid related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

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

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Postgrid through Composio's Tool Router. The agent can perform Postgrid 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

How to build Postgrid MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Postgrid MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Postgrid MCP with Claude Agent SDK

Google ADK

Google ADK

Use Postgrid MCP with Google ADK

LangChain

LangChain

Use Postgrid MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Postgrid MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Postgrid MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Postgrid MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Postgrid MCP?

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

Can I use Tool Router MCP with CrewAI?

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 Postgrid tools.

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

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

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free