# How to integrate Google Drive MCP with LlamaIndex

```json
{
  "title": "How to integrate Google Drive MCP with LlamaIndex",
  "toolkit": "Google Drive",
  "toolkit_slug": "googledrive",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/googledrive/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/googledrive/framework/llama-index.md",
  "updated_at": "2026-05-06T08:14:20.203Z"
}
```

## 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 your team, add comment to project proposal document 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.

## Also integrate Google Drive with

- [ChatGPT](https://composio.dev/toolkits/googledrive/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/googledrive/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/googledrive/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/googledrive/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/googledrive/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/googledrive/framework/codex)
- [Cursor](https://composio.dev/toolkits/googledrive/framework/cursor)
- [VS Code](https://composio.dev/toolkits/googledrive/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/googledrive/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/googledrive/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/googledrive/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/googledrive/framework/cli)
- [Google ADK](https://composio.dev/toolkits/googledrive/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/googledrive/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/googledrive/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/googledrive/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/googledrive/framework/crew-ai)

## 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

| Tool slug | Name | Description |
|---|---|---|
| `GOOGLEDRIVE_ADD_FILE_SHARING_PREFERENCE` | Add file sharing preference | Modifies sharing permissions for an existing google drive file, granting a specified role to a user, group, domain, or 'anyone'. |
| `GOOGLEDRIVE_COPY_FILE` | Copy file | Duplicates an existing file in google drive, identified by its `file id`. |
| `GOOGLEDRIVE_CREATE_COMMENT` | Create Comment | Tool to create a comment on a file. use when you need to add a new comment to a specific file in google drive. |
| `GOOGLEDRIVE_CREATE_DRIVE` | Create Shared Drive | Tool to create a new shared drive. use when you need to programmatically create a new shared drive for collaboration or storage. |
| `GOOGLEDRIVE_CREATE_FILE` | Create File or Folder | Creates a new file or folder with metadata. use to create empty files or folders, or files with content by providing it in the request body (though this action primarily focuses on metadata creation). |
| `GOOGLEDRIVE_CREATE_FILE_FROM_TEXT` | Create a File from Text | Creates a new file in google drive from provided text content (up to 10mb), supporting various formats including automatic conversion to google workspace types. |
| `GOOGLEDRIVE_CREATE_FOLDER` | Create a folder | Creates 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. |
| `GOOGLEDRIVE_CREATE_REPLY` | Create Reply | Tool to create a reply to a comment in google drive. use when you need to respond to an existing comment on a file. |
| `GOOGLEDRIVE_CREATE_SHORTCUT_TO_FILE` | Create Shortcut to File/Folder | Tool to create a shortcut to a file or folder in google drive. use when you need to link to an existing drive item from another location without duplicating it. |
| `GOOGLEDRIVE_DELETE_COMMENT` | Delete Comment | Deletes a comment from a file. use when you need to remove a specific comment from a google drive file. |
| `GOOGLEDRIVE_DELETE_DRIVE` | Delete Shared Drive | Tool to permanently delete a shared drive. use when you need to remove a shared drive and its contents (if specified). |
| `GOOGLEDRIVE_DELETE_PERMISSION` | Delete Permission | Deletes a permission from a file by permission id. use when you need to revoke access for a specific user or group from a file. |
| `GOOGLEDRIVE_DELETE_REPLY` | Delete Reply | Tool to delete a specific reply by reply id. use when you need to remove a reply from a comment on a file. |
| `GOOGLEDRIVE_DOWNLOAD_FILE` | Download a file from Google Drive | Downloads a file from google drive by its id. for google workspace documents (docs, sheets, slides), optionally exports to a specified `mime type`. for other file types, downloads in their native format regardless of mime type. |
| `GOOGLEDRIVE_EDIT_FILE` | Edit File | Updates an existing google drive file by overwriting its entire content with new text (max 10mb). |
| `GOOGLEDRIVE_EMPTY_TRASH` | Empty Trash | Tool to permanently delete all of the user's trashed files. use when you want to empty the trash in google drive. |
| `GOOGLEDRIVE_FILES_MODIFY_LABELS` | Modify File Labels | Modifies the set of labels applied to a file. returns a list of the labels that were added or modified. use when you need to programmatically change labels on a google drive file, such as adding, updating, or removing them. |
| `GOOGLEDRIVE_FIND_FILE` | Find file | Tool to list or search for files and folders in google drive. use when you need to find specific files based on query criteria or list contents of a drive/folder. |
| `GOOGLEDRIVE_FIND_FOLDER` | Find folder | Tool to find a folder in google drive by its name and optionally a parent folder. use when you need to locate a specific folder to perform further actions like creating files in it or listing its contents. |
| `GOOGLEDRIVE_GENERATE_IDS` | Generate File IDs | Generates a set of file ids which can be provided in create or copy requests. use when you need to pre-allocate ids for new files or copies. |
| `GOOGLEDRIVE_GET_ABOUT` | Get about | Tool to retrieve information about the user, the user's drive, and system capabilities. use when you need to check storage quotas, user details, or supported import/export formats. |
| `GOOGLEDRIVE_GET_CHANGES_START_PAGE_TOKEN` | Get Changes Start Page Token | Tool to get the starting pagetoken for listing future changes in google drive. use this when you need to track changes to files and folders. |
| `GOOGLEDRIVE_GET_COMMENT` | Get Comment | Tool to get a comment by id. use when you need to retrieve a specific comment from a google drive file and have both the file id and comment id. |
| `GOOGLEDRIVE_GET_DRIVE` | Get Shared Drive | Tool to get a shared drive by id. use when you need to retrieve information about a specific shared drive. |
| `GOOGLEDRIVE_GET_FILE_METADATA` | Get File Metadata | Tool to get a file's metadata by id. use when you need to retrieve the metadata for a specific file in google drive. |
| `GOOGLEDRIVE_GET_PERMISSION` | Get Permission | Gets a permission by id. use this tool to retrieve a specific permission for a file or shared drive. |
| `GOOGLEDRIVE_GET_REPLY` | Get Reply | Tool to get a specific reply to a comment on a file. use when you need to retrieve the details of a particular reply. |
| `GOOGLEDRIVE_GET_REVISION` | Get Revision | Tool to get a specific revision's metadata by revision id. use when you need to retrieve information about a particular version of a file. |
| `GOOGLEDRIVE_GOOGLE_DRIVE_DELETE_FOLDER_OR_FILE_ACTION` | Delete folder or file | Tool to delete a file or folder in google drive. use when you need to permanently remove a specific file or folder using its id. note: this action is irreversible. |
| `GOOGLEDRIVE_HIDE_DRIVE` | Hide Shared Drive | Tool to hide a shared drive from the default view. use when you want to remove a shared drive from the user's main google drive interface without deleting it. |
| `GOOGLEDRIVE_LIST_CHANGES` | List Changes | Tool to list the changes for a user or shared drive. use when you need to track modifications to files and folders, such as creations, deletions, or permission changes. this action requires a `pagetoken` which can be initially obtained using the `get changes start page token` action or from a previous `list changes` response. |
| `GOOGLEDRIVE_LIST_COMMENTS` | List Comments | Tool to list all comments for a file in google drive. use when you need to retrieve comments associated with a specific file. |
| `GOOGLEDRIVE_LIST_FILE_LABELS` | List File Labels | Tool to list the labels on a file. use when you need to retrieve all labels associated with a specific file in google drive. |
| `GOOGLEDRIVE_LIST_FILES` | List Files and Folders | Tool to list a user's files and folders in google drive. use this to search or browse for files and folders based on various criteria. |
| `GOOGLEDRIVE_LIST_PERMISSIONS` | List Permissions | Tool to list a file's permissions. use when you need to retrieve all permissions associated with a specific file or shared drive. |
| `GOOGLEDRIVE_LIST_REPLIES_TO_COMMENT` | List Replies to Comment | Tool to list replies to a comment in google drive. use this when you need to retrieve all replies associated with a specific comment on a file. |
| `GOOGLEDRIVE_LIST_REVISIONS` | List File Revisions | Tool to list a file's revisions. use when you need to retrieve the revision history of a specific file in google drive. |
| `GOOGLEDRIVE_LIST_SHARED_DRIVES` | List Shared Drives | Tool to list the user's shared drives. use when you need to get a list of all shared drives accessible to the authenticated user. |
| `GOOGLEDRIVE_MOVE_FILE` | Move File | Tool to move a file from one folder to another in google drive. use when you need to reorganize files by changing their parent folder(s). |
| `GOOGLEDRIVE_STOP_WATCH_CHANNEL` | Stop Watch Channel | Tool to stop watching resources through a specified channel. use this when you want to stop receiving notifications for a previously established watch. |
| `GOOGLEDRIVE_UNHIDE_DRIVE` | Unhide Shared Drive | Tool to unhide a shared drive. use when you need to restore a shared drive to the default view. |
| `GOOGLEDRIVE_UNTRASH_FILE` | Untrash File | Tool to restore a file from the trash. use when you need to recover a deleted file. this action updates the file's metadata to set the 'trashed' property to false. |
| `GOOGLEDRIVE_UPDATE_COMMENT` | Update Comment | Tool to update an existing comment on a google drive file. use when you need to change the content or status (e.g., resolve) of a comment. |
| `GOOGLEDRIVE_UPDATE_DRIVE` | Update Shared Drive | Tool to update the metadata for a shared drive. use when you need to modify properties like the name, theme, background image, or restrictions of a shared drive. |
| `GOOGLEDRIVE_UPDATE_FILE_PUT` | Update File (Metadata) | Updates file metadata. uses patch semantics (partial update) as per google drive api v3. use this tool to modify attributes of an existing file like its name, description, or parent folders. note: this action currently supports metadata updates only. file content updates require multipart/related upload and are not yet implemented. |
| `GOOGLEDRIVE_UPDATE_FILE_REVISION_METADATA` | Update File Revision Metadata | Updates metadata of a file revision (e.g., keepforever, publish). use this tool to modify the metadata of a specific revision of a file in google drive. |
| `GOOGLEDRIVE_UPDATE_PERMISSION` | Update Permission | Tool to update a permission with patch semantics. use when you need to modify an existing permission for a file or shared drive. |
| `GOOGLEDRIVE_UPDATE_REPLY` | Update Reply | Tool to update a reply to a comment on a google drive file. use when you need to modify the content of an existing reply. |
| `GOOGLEDRIVE_UPLOAD_FILE` | Upload File | Uploads a file (max 5mb) to google drive, moving it to a specified folder if a valid folder id is provided, otherwise uploads to root. |
| `GOOGLEDRIVE_WATCH_CHANGES` | Watch Drive Changes | Tool to subscribe to changes for a user or shared drive in google drive. use when you need to monitor a google drive for modifications and receive notifications at a specified webhook url. |

## Supported Triggers

| Trigger slug | Name | Description |
|---|---|---|
| `GOOGLEDRIVE_COMMENT_ADDED_TRIGGER` | Comment Added (Docs/Sheets/Slides) | Triggers when a new comment is added to Google Docs, Sheets, or Slides. |
| `GOOGLEDRIVE_FILE_CREATED_TRIGGER` | File Created | Triggers when a new file is created/added in Google Drive. This trigger monitors files and fires when new files are detected. |
| `GOOGLEDRIVE_FILE_DELETED_OR_TRASHED_TRIGGER` | File Deleted or Trashed | Triggers when a file is moved to trash or permanently deleted in Google Drive. |
| `GOOGLEDRIVE_FILE_SHARED_PERMISSIONS_ADDED` | File Shared (Permissions Added) | Triggers when new sharing permissions are granted to a file or folder in Google Drive. This trigger monitors the Drive Changes API to detect files that changed and, for those files, compares their current permissions against previously seen permissions to identify newly added sharing entries. |
| `GOOGLEDRIVE_FILE_UPDATED_TRIGGER` | File Updated | Triggers when a file's metadata or content changes in Google Drive. Emits file ID, modification timestamp, and editor info. |
| `GOOGLEDRIVE_GOOGLE_DRIVE_CHANGES` | Google Drive Changes | Triggers when changes are detected in a Google Drive. |
| `GOOGLEDRIVE_NEW_FILE_MATCHING_QUERY_TRIGGER` | New File Matching Query | Triggers when a new Google Drive file matches a provided query. |

## Creating MCP Server - Stand-alone vs Composio SDK

The Google Drive MCP server is an implementation of the Model Context Protocol that connects your AI agent to Google Drive. It provides structured and secure access so your agent can perform Google Drive operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. 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

### 1. Getting API Keys for OpenAI, Composio, and Google Drive

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

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

### 4. Import modules

No description provided.
```python
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()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
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")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

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.
```python
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)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["googledrive"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Google Drive actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
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}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

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
```python
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!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Google Drive, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
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!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["googledrive"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Google Drive actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## 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

- [ChatGPT](https://composio.dev/toolkits/googledrive/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/googledrive/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/googledrive/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/googledrive/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/googledrive/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/googledrive/framework/codex)
- [Cursor](https://composio.dev/toolkits/googledrive/framework/cursor)
- [VS Code](https://composio.dev/toolkits/googledrive/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/googledrive/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/googledrive/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/googledrive/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/googledrive/framework/cli)
- [Google ADK](https://composio.dev/toolkits/googledrive/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/googledrive/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/googledrive/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/googledrive/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/googledrive/framework/crew-ai)

## Related Toolkits

- [Google Docs](https://composio.dev/toolkits/googledocs) - Google Docs is a cloud-based word processor that enables document creation and real-time collaboration. Its seamless sharing and version history make team editing and content management a breeze.
- [Google Super](https://composio.dev/toolkits/googlesuper) - Google Super is an all-in-one suite combining Gmail, Drive, Calendar, Sheets, Analytics, and more. It gives you a unified platform to manage your digital life, boosting productivity and organization.
- [Affinda](https://composio.dev/toolkits/affinda) - Affinda is an AI-powered document processing platform that automates data extraction from resumes, invoices, and more. It streamlines document-heavy workflows by turning files into structured, actionable data.
- [Agility cms](https://composio.dev/toolkits/agility_cms) - Agility CMS is a headless content management system for building and managing digital experiences across platforms. It lets teams update content quickly and deliver omnichannel experiences with ease.
- [Algodocs](https://composio.dev/toolkits/algodocs) - Algodocs is an AI-powered platform that automates data extraction from business documents. It delivers fast, secure, and accurate processing without templates or manual training.
- [Api2pdf](https://composio.dev/toolkits/api2pdf) - Api2Pdf is a REST API for generating PDFs from HTML, URLs, and documents using powerful engines like wkhtmltopdf and Headless Chrome. It streamlines document conversion and automation for developers and businesses.
- [Aryn](https://composio.dev/toolkits/aryn) - Aryn is an AI-powered platform for parsing, extracting, and analyzing data from unstructured documents. Use it to automate document processing and unlock actionable insights from your files.
- [Boldsign](https://composio.dev/toolkits/boldsign) - Boldsign is a digital eSignature platform for sending, signing, and tracking documents online. Organizations use it to automate agreements and manage legally binding workflows efficiently.
- [Boloforms](https://composio.dev/toolkits/boloforms) - BoloForms is an eSignature platform built for small businesses, offering unlimited signatures, templates, and forms. It simplifies digital document signing and team collaboration at a predictable, fixed price.
- [Box](https://composio.dev/toolkits/box) - Box is a cloud content management and file sharing platform for businesses. It helps teams securely store, organize, and collaborate on files from anywhere.
- [Carbone](https://composio.dev/toolkits/carbone) - Carbone is a blazing-fast report generator that turns JSON data into PDFs, Word docs, spreadsheets, and more using flexible templates. It lets you automate document creation at scale with minimal code.
- [Castingwords](https://composio.dev/toolkits/castingwords) - CastingWords is a transcription service specializing in human-powered, accurate transcripts via a simple API. Get seamless audio-to-text conversion for interviews, meetings, podcasts, and more.
- [Cloudconvert](https://composio.dev/toolkits/cloudconvert) - CloudConvert is a powerful file conversion service supporting over 200 file formats. It streamlines converting, compressing, and managing documents, media, and more, all in one place.
- [Cloudlayer](https://composio.dev/toolkits/cloudlayer) - Cloudlayer is a document and asset generation service for creating PDFs and images via API or SDKs. It lets you automate high-quality doc creation, saving dev time and reducing manual work.
- [Cloudpress](https://composio.dev/toolkits/cloudpress) - Cloudpress is a content export tool for Google Docs and Notion. It automates publishing to your favorite Content Management Systems.
- [Contentful graphql](https://composio.dev/toolkits/contentful_graphql) - Contentful graphql is a content delivery API that lets you access Contentful data using GraphQL queries. It gives you efficient, flexible ways to fetch and manage structured content for any digital project.
- [Conversion tools](https://composio.dev/toolkits/conversion_tools) - Conversion Tools is an online service for converting documents between formats such as PDF, Word, Excel, XML, and CSV. It lets you automate complex document workflows with just a few clicks.
- [Convertapi](https://composio.dev/toolkits/convertapi) - ConvertAPI is a robust file conversion service for documents, images, and spreadsheets. It streamlines programmatic format changes and lets developers automate complex workflows with a single API.
- [Craftmypdf](https://composio.dev/toolkits/craftmypdf) - CraftMyPDF is a web-based service for designing and generating PDFs with templates and live data. It streamlines document creation by automating personalized PDFs at scale.
- [Docmosis](https://composio.dev/toolkits/docmosis) - Docmosis generates PDF and Word documents from user-defined templates. It's perfect for merging data fields to quickly produce reports, invoices, and business letters.

## Frequently Asked Questions

### 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.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)