How to integrate Google Drive MCP with LlamaIndex

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Google Drive Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Google Drive to LlamaIndex using the Composio tool router. By the end, you'll have a working Google Drive agent that can create a new folder named 'invoices', share last uploaded file with my team, add comment to project proposal document, copy template file to today's reports folder through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Google Drive account through Composio's Google Drive 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:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Google Drive
  • Connect LlamaIndex to the Google Drive MCP server
  • Build a Google Drive-powered agent using LlamaIndex
  • Interact with Google Drive through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

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

The Googledrive 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 Drive account. It provides structured and secure access to your files and folders, so your agent can perform actions like uploading files, managing sharing permissions, organizing folders, and collaborating via comments on your behalf.

  • Automated file uploads and creation: Effortlessly ask your agent to create new files or folders, upload documents, or generate files from provided text content in your Google Drive.
  • Advanced sharing and permission management: Let your agent modify sharing preferences for files and folders, granting or revoking access to users, groups, domains, or the public.
  • Collaboration through comments and replies: Have the agent add comments to files, reply to existing comments, or delete comments to facilitate smooth collaboration with your team.
  • Efficient folder and shortcut organization: Direct your agent to create, organize, or nest folders, or generate shortcuts to important files and folders for easier access.
  • File duplication and backup: Instruct your agent to duplicate existing files, creating reliable backups or templates for repeated use.

Supported Tools & Triggers

Tools
Triggers
Add file sharing preferenceModifies sharing permissions for an existing google drive file, granting a specified role to a user, group, domain, or 'anyone'.
Copy fileDuplicates an existing file in google drive, identified by its `file id`.
Create CommentTool to create a comment on a file.
Create Shared DriveTool to create a new shared drive.
Create File or FolderCreates a new file or folder with metadata.
Create a File from TextCreates a new file in google drive from provided text content (up to 10mb), supporting various formats including automatic conversion to google workspace types.
Create a folderCreates a new folder in google drive, optionally within a parent folder specified by its id or name; if a parent name is provided but not found, the action will fail.
Create ReplyTool to create a reply to a comment in google drive.
Create Shortcut to File/FolderTool to create a shortcut to a file or folder in google drive.
Delete CommentDeletes a comment from a file.
Delete Shared DriveTool to permanently delete a shared drive.
Delete PermissionDeletes a permission from a file by permission id.
Delete ReplyTool to delete a specific reply by reply id.
Download a file from Google DriveDownloads a file from google drive by its id.
Edit FileUpdates an existing google drive file by overwriting its entire content with new text (max 10mb).
Empty TrashTool to permanently delete all of the user's trashed files.
Modify File LabelsModifies the set of labels applied to a file.
Find fileTool to list or search for files and folders in google drive.
Find folderTool to find a folder in google drive by its name and optionally a parent folder.
Generate File IDsGenerates a set of file ids which can be provided in create or copy requests.
Get aboutTool to retrieve information about the user, the user's drive, and system capabilities.
Get Changes Start Page TokenTool to get the starting pagetoken for listing future changes in google drive.
Get CommentTool to get a comment by id.
Get Shared DriveTool to get a shared drive by id.
Get File MetadataTool to get a file's metadata by id.
Get PermissionGets a permission by id.
Get ReplyTool to get a specific reply to a comment on a file.
Get RevisionTool to get a specific revision's metadata by revision id.
Delete folder or fileTool to delete a file or folder in google drive.
Hide Shared DriveTool to hide a shared drive from the default view.
List ChangesTool to list the changes for a user or shared drive.
List CommentsTool to list all comments for a file in google drive.
List File LabelsTool to list the labels on a file.
List Files and FoldersTool to list a user's files and folders in google drive.
List PermissionsTool to list a file's permissions.
List Replies to CommentTool to list replies to a comment in google drive.
List File RevisionsTool to list a file's revisions.
List Shared DrivesTool to list the user's shared drives.
Move FileTool to move a file from one folder to another in google drive.
Stop Watch ChannelTool to stop watching resources through a specified channel.
Unhide Shared DriveTool to unhide a shared drive.
Untrash FileTool to restore a file from the trash.
Update CommentTool to update an existing comment on a google drive file.
Update Shared DriveTool to update the metadata for a shared drive.
Update File (Metadata)Updates file metadata.
Update File Revision MetadataUpdates metadata of a file revision (e.
Update PermissionTool to update a permission with patch semantics.
Update ReplyTool to update a reply to a comment on a google drive file.
Upload FileUploads a file (max 5mb) to google drive, moving it to a specified folder if a valid folder id is provided, otherwise uploads to root.
Watch Drive ChangesTool to subscribe to changes for a user or shared drive in google drive.

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 you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Google Drive account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Google Drive

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Google Drive access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called google drive_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["googledrive"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Google Drive actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Google Drive actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, google drive)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Google Drive tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Google Drive database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Google Drive

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Google Drive, then start asking questions.

Complete Code

Here's the complete code to get you started with Google Drive and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["googledrive"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Google Drive actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Google Drive actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Google Drive to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Google Drive tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Google Drive MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Google Drive MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Google Drive MCP with Claude Agent SDK

Google ADK

Google ADK

Use Google Drive MCP with Google ADK

LangChain

LangChain

Use Google Drive MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Google Drive MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Google Drive MCP with Mastra AI

CrewAI

CrewAI

Use Google Drive MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Google Drive MCP?

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Drive tools.

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

Yes, absolutely. You can configure which Google Drive 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 Google Drive 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