SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Google Admin MCP with Pydantic AI

Connect Pydantic AI to Google Admin MCP. Add new employee to all-staff group, list all users in marketing department, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Google Admin logoGoogle Admin
Oauth2

Google Admin is the central console for managing Google Workspace users, groups, and organizational units. It streamlines organizational control, saving admins time and reducing errors.

14 Tools

Introduction

This guide walks you through connecting Google Admin to Pydantic AI using the Composio tool router. By the end, you'll have a working Google Admin agent that can create and suspend Google Workspace users, manage groups and members, add email aliases, and update group settings through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Google Admin account through Composio's Google Admin MCP server.

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

Also integrate Google Admin with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

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 Google Admin
  • 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 Google Admin 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 Google Admin MCP server, and what's possible with it?

The Google Admin MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Google Admin account. It provides structured and secure access to your organization's Google Workspace admin console, so your agent can manage users, groups, aliases, and group settings on your behalf.

  • Automated user management: Easily create, suspend, or delete Google Workspace user accounts, letting your agent handle onboarding, offboarding, and user details with precision.
  • Group administration and membership control: Have your agent create groups, list all group members, add or remove users from groups, and fetch group details to streamline team management.
  • Email alias assignment: Direct your agent to add email aliases to user accounts, simplifying communication and identity management for your organization.
  • Comprehensive user and group directory access: Ask your agent to list all users or groups in your domain, filter them as needed, and retrieve detailed information to support audits or directory syncs.
  • Secure and efficient admin operations: Let your agent perform sensitive admin actions like deleting users or managing group settings—always with proper access controls and auditability.

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 Google Admin
  • 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 Google Admin
  • MCPServerStreamableHTTP connects to the Google Admin 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 Google Admin
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["google_admin"],
    )
    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 Google Admin 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
google_admin_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[google_admin_mcp],
    instructions=(
        "You are a Google Admin assistant. Use Google Admin tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Google Admin endpoint
  • The agent uses GPT-5 to interpret user commands and perform Google Admin 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 Google Admin.\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
  • Google Admin 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 Google Admin 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 Google Admin
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["google_admin"],
    )
    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
    google_admin_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[google_admin_mcp],
        instructions=(
            "You are a Google Admin assistant. Use Google Admin 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 Google Admin.\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 Google Admin through Composio's Tool Router. With this setup, your agent can perform real Google Admin 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 + Google Admin 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 Google Admin action and event your agent gets out of the box.

Add Alias to Google Workspace User

Adds an email alias to a Google Workspace user.

Add User to Google Workspace Group

Adds a user to a Google Workspace group with the specified role.

Create Google Workspace Group

Creates a new Google Workspace group with the specified details.

Create Google Workspace User

Creates a new Google Workspace user with the specified details.

Delete Google Workspace User

Deletes a Google Workspace user.

Get Google Workspace Group Details

Retrieves detailed information about a Google Workspace group.

Get Google Workspace User Details

Retrieves detailed information about a Google Workspace user.

List Google Workspace Group Members

Lists all members of a Google Workspace group with optional filtering and pagination.

List Google Workspace Groups

Lists Google Workspace groups with optional filtering and pagination.

List Google Workspace Users

Lists Google Workspace users with optional filtering and pagination.

Remove Alias from Google Workspace User

Removes an email alias from a Google Workspace user.

Remove User from Google Workspace Group

Removes a user from a Google Workspace group, revoking their group access.

Suspend/Unsuspend Google Workspace User

Suspends or unsuspends a Google Workspace user account.

Update Google Workspace Group Settings

Updates a Google Workspace group's display name and/or description.

FRAMEWORKS

How to build Google Admin MCP Agent with another framework

Claude Code logo

Claude Code

Use Google Admin MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Google Admin MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Google Admin MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Google Admin MCP with Claude Agent SDK

Codex logo

Codex

Use Google Admin MCP with Codex

OpenClaw logo

OpenClaw

Use Google Admin MCP with OpenClaw

Hermes logo

Hermes

Use Google Admin MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Google Admin MCP with Atomic Agent

Google ADK logo

Google ADK

Use Google Admin MCP with Google ADK

LangChain logo

LangChain

Use Google Admin MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Google Admin MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Google Admin MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Google Admin MCP with LlamaIndex

CrewAI logo

CrewAI

Use Google Admin MCP with CrewAI

AutoGen logo

AutoGen

Use Google Admin MCP with AutoGen

FAQ

Frequently asked questions

Start with Google Admin.It takes 30 seconds.

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

Start building