How to integrate Connecteam MCP with Pydantic AI

Connect Pydantic AI to Connecteam MCP. Archive users who have left the company, create new staff accounts for onboarding, and more using natural language, with authentication handled for you.

Connecteam logoConnecteam
Api Key

Connecteam is a workforce management platform for deskless teams, streamlining operations, HR, and team communication. It helps businesses save time by automating scheduling, time tracking, and staff engagement tasks.

35 Tools

Introduction

This guide walks you through connecting Connecteam to Pydantic AI using the Composio tool router. By the end, you'll have a working Connecteam agent that can create and archive users, list jobs and schedulers, browse forms and task boards, view chats, and check smart groups through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Connecteam account through Composio's Connecteam 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 Connecteam with

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Connecteam
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Connecteam workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Connecteam MCP server, and what's possible with it?

The Connecteam MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Connecteam account. It provides structured and secure access to your workforce management data, so your agent can perform actions like managing users, retrieving chats, processing forms, handling jobs, and analyzing performance metrics on your behalf.

  • User management and automation: Quickly add new employees, archive inactive users, or update user details to keep your workforce roster up to date.
  • Team communications monitoring: Retrieve chat conversations and team channels, making it easy for your agent to help you stay on top of internal messages and updates.
  • Form and workflow processing: List and review all existing forms, so your agent can help automate routine HR tasks and data collection.
  • Job and scheduling insights: Access job objects tied to your schedules or time clocks, letting your agent assist with workforce planning and role assignments.
  • Performance and policy analytics: Fetch performance indicators and available time-off policy types, enabling your agent to surface key metrics and streamline HR policy management.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active 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

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Connecteam
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
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

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Connecteam
  • MCPServerStreamableHTTP connects to the Connecteam MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Connecteam
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["connecteam"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Connecteam 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
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
connecteam_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[connecteam_mcp],
    instructions=(
        "You are a Connecteam assistant. Use Connecteam tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Connecteam endpoint
  • The agent uses GPT-5 to interpret user commands and perform Connecteam operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Connecteam.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Connecteam API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Connecteam and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Connecteam
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["connecteam"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    connecteam_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[connecteam_mcp],
        instructions=(
            "You are a Connecteam assistant. Use Connecteam tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Connecteam.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

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

Conclusion

You've built a Pydantic AI agent that can interact with Connecteam through Composio's Tool Router. With this setup, your agent can perform real Connecteam actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Connecteam for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Connecteam action and event your agent gets out of the box.

Archive Users

Tool to archive one or more users by their unique IDs.

Create Daily Note

Create a daily note for qualified users or groups.

Create Jobs

Create parent jobs or add sub-jobs beneath existing parent jobs.

Create Shifts

Create shifts without notifications by default.

Create Time Activities

Create shifts or breaks, optionally splitting existing shifts around breaks.

Create Users

Tool to create multiple users in Connecteam.

Delete Geofence

Delete one geofence and automatically verify its absence.

Delete Job

Delete a standalone job by ID.

Delete Shift

Delete one shift from a scheduler.

Delete Time Activity

Delete one shift or manual-break activity from a time clock.

Generate Upload URL

Tool to generate a pre-signed URL for uploading a file.

Get Chat

Retrieve a page of chat conversations, including team chats and channels.

Get Custom Field Categories

Tool to retrieve all custom field categories.

Get Custom Fields

Retrieve custom fields associated with the account, with options to filter, sort, and page through results.

Get Forms

Tool to retrieve all form definitions from Connecteam.

Get Form Submissions

Retrieve submissions for a form, optionally filtered by user or submit time.

Get Geofences

List all geofences configured for a time clock.

Get Jobs

Tool to retrieve a list of job objects relevant to a specific instance ID.

Get Pay Rates

Retrieve effective user pay rates over a required date range.

Get Performance Indicators

Tool to retrieve the list of performance metric indicators.

Get Policy Balances

Retrieve a page of user balances for a time-off policy type.

Get Policy Types

Tool to retrieve available time-off policy types.

Get Publishers

Retrieve a page of custom publishers associated with the account.

Get Schedulers

Tool to retrieve a list of job schedulers associated with the account.

Get Shifts

List shifts in a scheduler for a required Unix-time window.

Get Smart Groups

Tool to retrieve all smart groups associated with the account.

Get Task Boards

Tool to retrieve all task boards.

Get Time Activities

Retrieve shifts, manual breaks, and time off grouped by user.

Get Time Off Requests

Retrieve time-off requests overlapping a required date range.

Get Timesheet Totals

Retrieve payroll-oriented total hours for one time clock.

Get Users

Retrieve and filter a page of users associated with the account.

List Me

Tool to retrieve account information including company name and company ID.

Update Job

Update a standalone job or sub-job by ID.

Update Shifts

Update shifts; notifyUsers defaults true and may notify users for published shifts.

Update Users

Update up to 25 users, identifying every item by user ID or phone number.

FAQ

Frequently asked questions

Start with Connecteam.It takes 30 seconds.

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

Start building