How to integrate Google Chat MCP with Mastra AI

This guide walks you through connecting Google Chat to Mastra AI using the Composio tool router. By the end, you'll have a working Google Chat agent that can summarize recent messages in project space, send standup reminder to engineering space, list members of support chat space through natural language commands. This guide will help you understand how to give your Mastra AI agent real control over a Google Chat account through Composio's Google Chat MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Google Chat logoGoogle Chat
Oauth2

Google Chat is Google Workspace's messaging and collaboration service for teams. It keeps conversations, spaces, files, and work updates in one shared place.

45 Tools

Introduction

This guide walks you through connecting Google Chat to Mastra AI using the Composio tool router. By the end, you'll have a working Google Chat agent that can summarize recent messages in project space, send standup reminder to engineering space, list members of support chat space through natural language commands.

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

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

Also integrate Google Chat with

TL;DR

Here's what you'll learn:
  • Set up your environment so Mastra, OpenAI, and Composio work together
  • Create a Tool Router session in Composio that exposes Google Chat tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Google Chat tool definitions and attach them as a toolset
  • Build a Mastra agent that can reason, call tools, and return structured results
  • Run an interactive CLI where you can chat with your Google Chat agent

What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.

Key features include:

  • MCP Client: Built-in support for Model Context Protocol servers
  • Toolsets: Organize tools into logical groups
  • Step Callbacks: Monitor and debug agent execution
  • OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

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

The Google Chat 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 Chat account. It provides structured and secure access so your agent can perform Google Chat operations on your behalf.

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:
  • Node.js 18 or higher
  • A Composio account with an active API key
  • An OpenAI API key
  • Basic familiarity with TypeScript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key.
  • You need credits or a connected billing setup to use the models.
  • Store the key somewhere safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Google Chat through MCP.
3

Install dependencies

bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv

Install the required packages.

What's happening:

  • @composio/core is the Composio SDK for creating MCP sessions
  • @mastra/core provides the Agent class
  • @mastra/mcp is Mastra's MCP client
  • @ai-sdk/openai is the model wrapper for OpenAI
  • dotenv loads environment variables from .env
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_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 your requests to Composio
  • COMPOSIO_USER_ID tells Composio which user this session belongs to
  • OPENAI_API_KEY lets the Mastra agent call OpenAI models
5

Import libraries and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey as string,
});
What's happening:
  • dotenv/config auto loads your .env so process.env.* is available
  • openai gives you a Mastra compatible model wrapper
  • Agent is the Mastra agent that will call tools and produce answers
  • MCPClient connects Mastra to your Composio MCP server
  • Composio is used to create a Tool Router session
6

Create a Tool Router session for Google Chat

typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["google_chat"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Google Chat MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "google_chat" for Google Chat access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to
7

Configure Mastra MCP client and fetch tools

typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
What's happening:
  • MCPClient takes an id for this client and a list of MCP servers
  • The headers property includes the x-api-key for authentication
  • getTools fetches the tool definitions exposed by the Google Chat toolkit
8

Create the Mastra agent

typescript
const agent = new Agent({
    name: "google_chat-mastra-agent",
    instructions: "You are an AI agent with Google Chat tools via Composio.",
    model: "openai/gpt-5",
  });
What's happening:
  • Agent is the core Mastra agent
  • name is just an identifier for logging and debugging
  • instructions guide the agent to use tools instead of only answering in natural language
  • model uses openai("gpt-5") to configure the underlying LLM
9

Set up interactive chat interface

typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\n");

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

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;
  }

  messages.push({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        google_chat: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    console.log("\nSession ended.");
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Google Chat toolsets
  • maxSteps limits how many tool calls the agent can take in a single run
  • onStepFinish is a hook that prints intermediate steps for debugging

Complete Code

Here's the complete code to get you started with Google Chat and Mastra AI:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({ apiKey: composioAPIKey as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["google_chat"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      google_chat: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "google_chat-mastra-agent",
    instructions: "You are an AI agent with Google Chat tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { google_chat: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();

Conclusion

You've built a Mastra AI agent that can interact with Google Chat through Composio's Tool Router. You can extend this further by:
  • Adding other toolkits like Gmail, Slack, or GitHub
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows
TOOLS

Supported Tools

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

Complete Space Import

Completes the import process for an import-mode Google Chat space and makes it visible to users.

Create Custom Emoji

Creates a custom emoji in Google Chat for use within an organization.

Create Space Member

Creates a membership for a user, Chat app, or Google Group in a space.

Create Message

Creates a message in a Google Chat space.

Create Reaction

Creates an emoji reaction on a Google Chat message.

Create section

Creates a custom section in Google Chat for organizing conversations in the navigation panel.

Create Space

Creates a named space or group chat in Google Chat.

Delete Custom Emoji

Deletes a custom emoji from Google Chat.

Delete Member from Space

Removes a user, Google Group, or app from a space.

Delete Message

Deletes a message from a Google Chat space.

Delete Reaction

Deletes a reaction to a message.

Delete section

Deletes a custom section from Google Chat by its ID.

Delete space

Deletes a named space from Google Chat.

Download Media

Downloads the bytes of a Google Chat message attachment via the media API.

Find Direct Message

Returns the existing direct message space with the specified user.

Find Group Chats

Finds all group chat spaces that contain exactly the calling user and the specified users.

Get Attachment

Gets the metadata of a Google Chat message attachment.

Get Custom Emoji

Returns details about a custom emoji in Google Chat.

Get Chat Space Member

Returns details about a membership in a space.

Get Message

Returns details about a specific message in a Google Chat space.

Get Space

Returns details about a specific Google Chat space including configuration, membership count, and access settings.

Get Space Event

Returns an event from a Google Chat space.

Get Space Notification Setting

Gets the notification settings for a user in a specific space.

Get space read state

Returns details about a user's read state within a space.

Get thread read state

Returns details about a user's read state within a thread.

List custom emojis

Lists custom emojis visible to the authenticated user in Google Chat.

List Space Members

Lists memberships in a space.

List Messages

Lists messages in a space that the authenticated user is a member of.

List reactions on a message

Lists all reactions on a specific message in a Google Chat space.

List Section Items

Lists all items (such as spaces) within a specified section of a user's Google Chat.

List Sections

Lists all sections available to the authenticated user in Google Chat.

List Space Events

Lists events from a Google Chat space.

List Spaces

Lists spaces the authenticated user is a member of in Google Chat.

Move Section Item

Moves a space from one section to another in Google Chat.

Position Section in Sidebar

Changes the sort order of a section in the Google Chat sidebar.

Replace Message (Full)

Replaces an existing message in a Google Chat space using full replacement.

Search Spaces

Searches for spaces across a Google Workspace organization using administrator privileges.

Setup Space

Creates a space and adds specified users and groups to it.

Update Member

Updates a membership in a Google Chat space, such as changing a member's role between member and manager.

Update Message

Updates a message in a Google Chat space, modifying its text, cards, or other properties.

Update section

Updates a section's display name in Google Chat.

Update Space

Updates a Google Chat space's configuration including display name, description, guidelines, history settings, access settings, and permission settings.

Update Space Notification Setting

Updates the notification settings for a user in a space.

Update Space Read State

Updates a user's read state within a space, used to mark messages as read or unread.

Upload Media Attachment

Uploads a file as an attachment to a Google Chat space using the multipart media upload endpoint.

FAQ

Frequently asked questions

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

Yes, you can. Mastra AI 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 Google Chat tools.

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

Start with Google Chat.It takes 30 seconds.

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

Start building