# How to integrate Google Sheets MCP with LlamaIndex

```json
{
  "title": "How to integrate Google Sheets MCP with LlamaIndex",
  "toolkit": "Google Sheets",
  "toolkit_slug": "googlesheets",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/googlesheets/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/googlesheets/framework/llama-index.md",
  "updated_at": "2026-05-06T08:14:27.288Z"
}
```

## Introduction

This guide walks you through connecting Google Sheets to LlamaIndex using the Composio tool router. By the end, you'll have a working Google Sheets agent that can add a new sheet named 'q3 sales', update all rows where status is 'pending', create a pie chart of expenses by category through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Google Sheets account through Composio's Google Sheets MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Google Sheets with

- [ChatGPT](https://composio.dev/toolkits/googlesheets/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/googlesheets/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/googlesheets/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/googlesheets/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/googlesheets/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/googlesheets/framework/codex)
- [Cursor](https://composio.dev/toolkits/googlesheets/framework/cursor)
- [VS Code](https://composio.dev/toolkits/googlesheets/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/googlesheets/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/googlesheets/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/googlesheets/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/googlesheets/framework/cli)
- [Google ADK](https://composio.dev/toolkits/googlesheets/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/googlesheets/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/googlesheets/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/googlesheets/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/googlesheets/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 Sheets
- Connect LlamaIndex to the Google Sheets MCP server
- Build a Google Sheets-powered agent using LlamaIndex
- Interact with Google Sheets 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 Sheets MCP server, and what's possible with it?

The Google Sheets 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 Sheets account. It provides structured and secure access to your spreadsheets, so your agent can perform actions like creating new sheets, updating data, generating charts, and automating spreadsheet workflows on your behalf.
- Spreadsheet creation and management: Instantly create new Google Sheets and add new worksheets (tabs) to existing spreadsheets whenever you need extra space or organization.
- Bulk data reading and updating: Retrieve specific data ranges, aggregate column data, or update multiple rows and cells at once—perfect for reporting or syncing external data.
- Automated chart generation: Direct your agent to build charts from selected data, making visualization and analysis faster and easier right inside your sheets.
- Smart filtering and data cleanup: Have the agent clear filters, remove cell contents, or append rows and columns to keep your sheets tidy and up to date.
- Dynamic data manipulation: Use advanced features like batch updates with data filters and aggregate operations to transform, filter, or summarize spreadsheet data efficiently.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `GOOGLESHEETS_ADD_SHEET` | Add Sheet to Spreadsheet | Adds a new sheet (worksheet) to a spreadsheet. use this tool to create a new tab within an existing google sheet, optionally specifying its title, index, size, and other properties. |
| `GOOGLESHEETS_AGGREGATE_COLUMN_DATA` | Aggregate Column Data | Searches for rows where a specific column matches a value and performs mathematical operations on data from another column. |
| `GOOGLESHEETS_APPEND_DIMENSION` | Append Dimension | Tool to append new rows or columns to a sheet, increasing its size. use when you need to add empty rows or columns to an existing sheet. |
| `GOOGLESHEETS_BATCH_GET` | Batch get spreadsheet | Retrieves data from specified cell ranges in a google spreadsheet; ensure the spreadsheet has at least one worksheet and any explicitly referenced sheet names in ranges exist. |
| `GOOGLESHEETS_BATCH_UPDATE` | Batch update spreadsheet | Updates a specified range in a google sheet with given values, or appends them as new rows if `first cell location` is omitted; ensure the target sheet exists and the spreadsheet contains at least one worksheet. |
| `GOOGLESHEETS_BATCH_UPDATE_VALUES_BY_DATA_FILTER` | Batch Update Values by Data Filter | Tool to update values in ranges matching data filters. use when you need to update specific data in a google sheet based on criteria rather than fixed cell ranges. |
| `GOOGLESHEETS_CLEAR_BASIC_FILTER` | Clear Basic Filter | Tool to clear the basic filter from a sheet. use when you need to remove an existing basic filter from a specific sheet within a google spreadsheet. |
| `GOOGLESHEETS_CLEAR_VALUES` | Clear spreadsheet values | Clears cell content (preserving formatting and notes) from a specified a1 notation range in a google spreadsheet; the range must correspond to an existing sheet and cells. |
| `GOOGLESHEETS_CREATE_CHART` | Create Chart in Google Sheets | Create a chart in a google sheets spreadsheet using the specified data range and chart type. |
| `GOOGLESHEETS_CREATE_GOOGLE_SHEET1` | Create a Google Sheet | Creates a new google spreadsheet in google drive using the provided title. |
| `GOOGLESHEETS_CREATE_SPREADSHEET_COLUMN` | Create spreadsheet column | Creates a new column in a google spreadsheet, requiring a valid `spreadsheet id` and an existing `sheet id`; an out-of-bounds `insert index` may append/prepend the column. |
| `GOOGLESHEETS_CREATE_SPREADSHEET_ROW` | Create spreadsheet row | Inserts a new, empty row into a specified sheet of a google spreadsheet at a given index, optionally inheriting formatting from the row above. |
| `GOOGLESHEETS_DELETE_DIMENSION` | Delete Dimension (Rows/Columns) | Tool to delete specified rows or columns from a sheet in a google spreadsheet. use when you need to remove a range of rows or columns. |
| `GOOGLESHEETS_DELETE_SHEET` | Delete Sheet | Tool to delete a sheet (worksheet) from a spreadsheet. use when you need to remove a specific sheet from a google sheet document. |
| `GOOGLESHEETS_EXECUTE_SQL` | Execute SQL on Spreadsheet | Execute sql queries against google sheets tables. supports select, insert, update, and delete operations with familiar sql syntax. tables are automatically detected and mapped from the spreadsheet structure. |
| `GOOGLESHEETS_FIND_WORKSHEET_BY_TITLE` | Find worksheet by title | Finds a worksheet by its exact, case-sensitive title within a google spreadsheet; returns a boolean indicating if found and the complete metadata of the entire spreadsheet, regardless of whether the target worksheet is found. |
| `GOOGLESHEETS_FORMAT_CELL` | Format cell | Applies text and background cell formatting to a specified range in a google sheets worksheet. |
| `GOOGLESHEETS_GET_SHEET_NAMES` | Get sheet names | Lists all worksheet names from a specified google spreadsheet (which must exist), useful for discovering sheets before further operations. |
| `GOOGLESHEETS_GET_SPREADSHEET_BY_DATA_FILTER` | Get Spreadsheet by Data Filter | Returns the spreadsheet at the given id, filtered by the specified data filters. use this tool when you need to retrieve specific subsets of data from a google sheet based on criteria like a1 notation, developer metadata, or grid ranges. |
| `GOOGLESHEETS_GET_SPREADSHEET_INFO` | Get spreadsheet info | Retrieves comprehensive metadata for a google spreadsheet using its id, excluding cell data. |
| `GOOGLESHEETS_GET_TABLE_SCHEMA` | Get Table Schema | This action is used to get the schema of a table in a google spreadsheet, call this action to get the schema of a table in a spreadsheet before you query the table. analyze table structure and infer column names, types, and constraints. uses statistical analysis of sample data to determine the most likely data type for each column. call this action after calling the list tables action to get the schema of a table in a spreadsheet. |
| `GOOGLESHEETS_INSERT_DIMENSION` | Insert Dimension in Google Sheet | Tool to insert new rows or columns into a sheet at a specified location. use when you need to add empty rows or columns within an existing google sheet. |
| `GOOGLESHEETS_LIST_TABLES` | List Tables in Spreadsheet | This action is used to list all tables in a google spreadsheet, call this action to get the list of tables in a spreadsheet. discover all tables in a google spreadsheet by analyzing sheet structure and detecting data patterns. uses heuristic analysis to find header rows, data boundaries, and table structures. |
| `GOOGLESHEETS_LOOKUP_SPREADSHEET_ROW` | Look up spreadsheet row | Finds the first row in a google spreadsheet where a cell's entire content exactly matches the query string, searching within a specified a1 notation range or the first sheet by default. |
| `GOOGLESHEETS_QUERY_TABLE` | Query Spreadsheet Table | This action is used to query a table in a google spreadsheet, call this action to query a table in a spreadsheet. execute sql-like select queries against spreadsheet tables. supports where conditions, order by, limit clauses. call this action after calling the get table schema action to query a table in a spreadsheet. |
| `GOOGLESHEETS_SEARCH_DEVELOPER_METADATA` | Search Developer Metadata | Tool to search for developer metadata in a spreadsheet. use when you need to find specific metadata entries based on filters. |
| `GOOGLESHEETS_SEARCH_SPREADSHEETS` | Search Spreadsheets | Search for google spreadsheets using various filters including name, content, date ranges, and more. |
| `GOOGLESHEETS_SET_BASIC_FILTER` | Set Basic Filter | Tool to set a basic filter on a sheet in a google spreadsheet. use when you need to filter or sort data within a specific range on a sheet. |
| `GOOGLESHEETS_SHEET_FROM_JSON` | Create sheet from JSON | Creates a new google spreadsheet and populates its first worksheet from `sheet json`, which must be non-empty as its first item's keys establish the headers. |
| `GOOGLESHEETS_SPREADSHEETS_SHEETS_COPY_TO` | Copy Sheet to Another Spreadsheet | Tool to copy a single sheet from a spreadsheet to another spreadsheet. use when you need to duplicate a sheet into a different spreadsheet. |
| `GOOGLESHEETS_SPREADSHEETS_VALUES_APPEND` | Append Values to Spreadsheet | Tool to append values to a spreadsheet. use when you need to add new data to the end of an existing table in a google sheet. |
| `GOOGLESHEETS_SPREADSHEETS_VALUES_BATCH_CLEAR` | Batch Clear Spreadsheet Values | Tool to clear one or more ranges of values from a spreadsheet. use when you need to remove data from specific cells or ranges while keeping formatting and other properties intact. |
| `GOOGLESHEETS_SPREADSHEETS_VALUES_BATCH_CLEAR_BY_DATA_FILTER` | Batch Clear Values By Data Filter | Clears one or more ranges of values from a spreadsheet using data filters. the caller must specify the spreadsheet id and one or more datafilters. ranges matching any of the specified data filters will be cleared. only values are cleared -- all other properties of the cell (such as formatting, data validation, etc..) are kept. |
| `GOOGLESHEETS_SPREADSHEETS_VALUES_BATCH_GET_BY_DATA_FILTER` | Batch Get Spreadsheet Values by Data Filter | Tool to return one or more ranges of values from a spreadsheet that match the specified data filters. use when you need to retrieve specific data sets based on filtering criteria rather than entire sheets or fixed ranges. |
| `GOOGLESHEETS_UPDATE_SHEET_PROPERTIES` | Update Sheet Properties | Tool to update properties of a sheet (worksheet) within a google spreadsheet, such as its title, index, visibility, tab color, or grid properties. use this when you need to modify the metadata or appearance of a specific sheet. |
| `GOOGLESHEETS_UPDATE_SPREADSHEET_PROPERTIES` | Update Spreadsheet Properties | Tool to update properties of a spreadsheet, such as its title, locale, or auto-recalculation settings. use when you need to modify the overall configuration of a google sheet. |

## Supported Triggers

| Trigger slug | Name | Description |
|---|---|---|
| `GOOGLESHEETS_AGGREGATE_METRIC_CHANGED_TRIGGER` | Aggregate Metric Changed | Triggers when an aggregate metric (SUM/COUNT/AVG/MIN/MAX) changes in a Google Sheets spreadsheet. This trigger monitors an aggregate calculation on a target column (optionally filtered by a search column/value) and fires when the calculated result changes. |
| `GOOGLESHEETS_CELL_RANGE_VALUES_CHANGED_TRIGGER` | Cell Range Values Changed | Triggers when values in a specified A1 range change in Google Sheets. This trigger monitors a specific cell or range of cells and fires when any values change. |
| `GOOGLESHEETS_CONDITIONAL_FORMAT_RULE_CHANGED_TRIGGER` | Conditional Format Rule Changed | Triggers when conditional formatting rules change in a Google Spreadsheet. Detects when rules are added, updated, or removed. Uses snapshot-based diffing to detect changes between polls. |
| `GOOGLESHEETS_DATA_VALIDATION_RULE_CHANGED_TRIGGER` | Data Validation Rule Changed | Triggers when data validation rules change (added/updated/removed) in a Google Spreadsheet. Uses snapshot-based diffing to detect changes between polls. |
| `GOOGLESHEETS_DEVELOPER_METADATA_CHANGED_TRIGGER` | Developer Metadata Changed | Triggers when developer metadata entries change (new/updated/removed) in a Google Spreadsheet. Uses snapshot-based diffing to detect changes between polls. |
| `GOOGLESHEETS_FILTERED_RANGE_VALUES_CHANGED_TRIGGER` | Filtered Range Values Changed | Polling trigger that monitors Google Sheets filtered ranges for value changes. Uses snapshot-based diffing to detect when values matching a data filter change. Emits the matched values when changes are detected. |
| `GOOGLESHEETS_NEW_ROWS_TRIGGER` | New Rows in Google Sheet | Simple polling trigger that monitors Google Sheets for new rows. Detects when new rows are added and returns the complete row data. Perfect for triggering any workflow based on new sheet entries. |
| `GOOGLESHEETS_NEW_SHEET_ADDED_TRIGGER` | New Sheet Added in Google Spreadsheet | Polling trigger that detects when a new sheet is added to a Google Spreadsheet. |
| `GOOGLESHEETS_NEW_SPREADSHEET_CREATED_TRIGGER` | New Spreadsheet Created | Triggers when a new Google Spreadsheet is created. This trigger monitors Google Spreadsheets and fires when new spreadsheets are detected. Uses timestamp filtering to efficiently detect newly created spreadsheets. |
| `GOOGLESHEETS_SPREADSHEET_METADATA_CHANGED_TRIGGER` | Spreadsheet Metadata Changed | Polling trigger that detects when a Google Spreadsheet's metadata changes. Uses snapshot-based diffing to detect any changes in spreadsheet properties, sheets, named ranges, developer metadata, data sources, etc. |
| `GOOGLESHEETS_SPREADSHEET_PROPERTIES_CHANGED_TRIGGER` | Spreadsheet Properties Changed | Polling trigger that detects when a Google Spreadsheet's top-level properties change. Monitors properties such as title, locale, timeZone, and autoRecalc settings. |
| `GOOGLESHEETS_SPREADSHEET_ROW_CHANGED_TRIGGER` | Spreadsheet Row Changed | Triggers when a looked-up spreadsheet row changes. This trigger monitors a specific row (located by searching for a query value within a user-specified range) and fires when the row's values change, when the row appears, or when the row disappears. |
| `GOOGLESHEETS_SPREADSHEET_SEARCH_MATCH_TRIGGER` | Spreadsheet Search Match | Triggers when a new spreadsheet appears that matches a saved search. This trigger uses snapshot-based diffing to detect when spreadsheets matching the search criteria are newly created or become visible to the user. |
| `GOOGLESHEETS_TABLE_QUERY_RESULT_CHANGED_TRIGGER` | Table Query Result Changed | Triggers when the result set of a saved table query changes in Google Sheets. Detects rows added, removed, or updated in the query output. This trigger monitors the result of a SQL query against a Google Sheets table and fires when changes are detected. |
| `GOOGLESHEETS_TABLE_SCHEMA_CHANGED_TRIGGER` | Table Schema Changed | Polling trigger that detects when a table's schema changes in Google Sheets. Monitors columns added/removed/renamed and inferred type/format changes. Uses snapshot-based diffing to compare schemas between polls. |
| `GOOGLESHEETS_WORKSHEET_NAMES_CHANGED_TRIGGER` | Worksheet Names Changed | Triggers when the set of worksheet/tab names changes in a Google Spreadsheet. Detects when sheets are added, deleted, or renamed. |

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

The Google Sheets MCP server is an implementation of the Model Context Protocol that connects your AI agent to Google Sheets. It provides structured and secure access so your agent can perform Google Sheets 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 Sheets account and project
- Basic familiarity with async Python/Typescript

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

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 Sheets 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 sheets)
- 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 Sheets 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=["googlesheets"],
    )

    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 Sheets actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Google Sheets 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: ["googlesheets"],
    },
  );

  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 Sheets 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 Sheets
```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 Sheets, 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=["googlesheets"],
    )

    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 Sheets actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Google Sheets 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: ["googlesheets"],
    },
  );

  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 Sheets 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 Sheets to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Google Sheets 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 Sheets MCP Agent with another framework

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

## Related Toolkits

- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.
- [ClickSend](https://composio.dev/toolkits/clicksend) - ClickSend is a cloud-based SMS and email marketing platform for businesses. It streamlines communication by enabling quick message delivery and contact management.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Google Sheets MCP?

With a standalone Google Sheets MCP server, the agents and LLMs can only access a fixed set of Google Sheets tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Google Sheets 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 Sheets tools.

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

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

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