# How to integrate Grist MCP with LlamaIndex

```json
{
  "title": "How to integrate Grist MCP with LlamaIndex",
  "toolkit": "Grist",
  "toolkit_slug": "grist",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/grist/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/grist/framework/llama-index.md",
  "updated_at": "2026-05-12T10:14:24.273Z"
}
```

## Introduction

This guide walks you through connecting Grist to LlamaIndex using the Composio tool router. By the end, you'll have a working Grist agent that can add new sales data to q2 table, create a document for project planning, delete outdated rows from inventory sheet through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Grist account through Composio's Grist MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Grist with

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

The Grist MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Grist account. It provides structured and secure access to your spreadsheets and documents, so your agent can perform actions like adding records, creating tables, managing documents, and handling attachments on your behalf.
- Automated data entry and record management: Instruct your agent to add, update, or delete records in specific Grist tables, streamlining your workflows and reducing manual input.
- Table and document creation: Let your agent create new tables or entire documents in your workspaces, helping you quickly set up and expand your data structures as your needs grow.
- Attachment and file management: Ask your agent to remove unwanted attachments from Grist documents, keeping your files organized and storage efficient.
- Custom webhook integration: Have your agent register or delete webhooks for documents, enabling real-time notifications and integrations with other tools or services you rely on.
- User and access provisioning via SCIM: Direct your agent to create or delete SCIM users as needed, making it easy to manage who has access to your Grist environment.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `GRIST_ADD_RECORDS` | Add Records | Add one or more records to a Grist table. First use GRIST_LIST_WORKSPACES to get docId, GRIST_LIST_TABLES to get tableId, and GRIST_LIST_COLUMNS to get column IDs for the fields mapping. |
| `GRIST_CREATE_DOCUMENT` | Create Document | Creates a new Grist document in a specified workspace. Use this tool when you need to add a new spreadsheet document to a workspace. Requires a valid workspace ID (obtainable via GRIST_LIST_WORKSPACES) and a document name. |
| `GRIST_CREATE_SCIM_USER` | Create SCIM User | Tool to create a new SCIM user. Use when provisioning new user accounts via SCIM. Run after gathering all required user details. |
| `GRIST_CREATE_TABLE` | Create Table | Tool to create tables in a document. Use after confirming the document ID. Creates one or more tables with specified columns in the given document. |
| `GRIST_CREATE_WEBHOOK` | Create Document Webhook | Tool to create a new webhook for a specified document. Use when you need to register webhook endpoints for document events in Grist. Run after confirming document ID. |
| `GRIST_DELETE_ATTACHMENT` | Remove Unused Attachments | Remove unused attachments from a Grist document to free up storage space. IMPORTANT: This action removes ALL attachments that are not currently referenced by any cell in the document. It does NOT delete a specific attachment by ID. To remove a specific attachment: 1. First remove its reference from the Attachments column cell that contains it 2. Then call this action to clean up the now-unreferenced file Attachments become "unused" when they are no longer referenced by any Attachments-type cell. Grist normally retains unreferenced attachments for a period to allow undo operations. This action removes them immediately (or only expired ones if expired_only=true). |
| `GRIST_DELETE_COLUMN` | Delete Column | Tool to delete a column from a Grist document table. Use after confirming document, table, and column IDs. |
| `GRIST_DELETE_RECORDS` | Delete Grist Table Records | Tool to delete records from a specified Grist table. Use when you need to remove specific rows by their IDs. Use after confirming the row IDs exist. |
| `GRIST_DELETE_SCIM_USER` | Delete SCIM User | Delete a user from the Grist organization by their numeric user ID. Use GRIST_GET_USERS first to find the user's ID. Falls back to org access API if SCIM is not enabled. Note: Cannot delete your own account. |
| `GRIST_DELETE_WEBHOOK` | Delete Webhook | Permanently removes a webhook from a Grist document. Use this tool when you need to stop receiving notifications for document changes. First use GRIST_LIST_WEBHOOKS to find the webhook_id you want to delete. This action is destructive and cannot be undone. |
| `GRIST_DOWNLOAD_ALL_ATTACHMENTS_ARCHIVE` | Download All Attachments Archive | Download all attachments from a Grist document as a single archive file (.zip or .tar). Use this to bulk-download attachments. Ensure the document has attachments before calling (check with GRIST_LIST_ATTACHMENTS). Returns an empty archive if no attachments exist. |
| `GRIST_DOWNLOAD_ATTACHMENT` | Download Attachment | Download a file attachment from a Grist document. Returns the file content as a downloadable file. Use GRIST_LIST_ATTACHMENTS first to get valid attachment IDs. |
| `GRIST_FETCH_DOCUMENT_METADATA` | Fetch Document Metadata | Tool to fetch metadata for a specified Grist document. Use after obtaining the document ID. |
| `GRIST_FETCH_TABLE_METADATA` | Fetch Table Metadata | Tool to retrieve metadata for a specified table in a Grist document. Use when you need to inspect table schema details before data operations. |
| `GRIST_GET_ORG_ACCESS` | Get Org Access | Retrieves the list of users who have access to a Grist organization along with their access roles (owners, editors, viewers). Use this to find user IDs, emails, or check access permissions within an organization. Useful for user management tasks. |
| `GRIST_GET_USERS` | Get Users | Tool to retrieve a list of users via SCIM v2. Use when you need to page through and filter enterprise users in Grist. |
| `GRIST_LIST_ATTACHMENTS` | List Attachments | Tool to list all attachments in a Grist document. Use after confirming the document ID to retrieve attachment metadata. |
| `GRIST_LIST_COLUMNS` | List Columns | Tool to list all columns in a specified Grist table. Use after selecting the document and table to inspect column metadata. |
| `GRIST_LIST_ORGANIZATIONS` | List Organizations | Tool to list all organizations accessible to the authenticated user. Use when you need to select a Grist organization for subsequent operations. |
| `GRIST_LIST_RECORDS` | List Records | Tool to retrieve records from a specified table within a Grist document. Use when you need to fetch rows by applying optional filters, sorting, limits, or hidden columns. Example: list records where pet is 'cat' sorted by '-age'. |
| `GRIST_LIST_TABLES` | List Tables | Tool to list all tables within a specified document. Use after obtaining the document ID to retrieve its tables. |
| `GRIST_LIST_WEBHOOKS` | List Webhooks | List all webhooks configured for a Grist document. Returns webhook configuration details (URL, event types, table binding) and delivery status information. Use this to inspect, audit, or manage webhooks for a document. Requires a valid document ID obtained from GRIST_LIST_WORKSPACES or GRIST_CREATE_DOCUMENT. |
| `GRIST_LIST_WORKSPACES` | List Workspaces | Tool to list all workspaces and documents accessible to the authenticated user on the current site. Use when you need to select a workspace or document for subsequent operations. |
| `GRIST_RUN_SQL_QUERY` | Run SQL Query | Tool to execute a read-only SQL SELECT query on a Grist document. Use after confirming the document ID and preparing a valid SQL SELECT statement. |
| `GRIST_UPDATE_COLUMN_METADATA` | Update Column Metadata | Updates metadata (label, type, description, formula, etc.) for one or more columns in a Grist table. Use List Columns first to get valid column IDs. Warning: changing 'label' may rename the column ID unless 'untieColIdFromLabel' is set to true. |
| `GRIST_UPDATE_DOCUMENT_METADATA` | Update Document Metadata | Tool to update metadata for a specified Grist document. Use when you need to rename or pin/unpin a document after obtaining its ID. |
| `GRIST_UPDATE_RECORDS` | Update Records | Update existing records in a Grist table by their row IDs. Use this tool to modify field values for one or more records in a specified document and table. First use GRIST_LIST_RECORDS to obtain the record IDs you want to update. Supports batch updates - you can update multiple records in a single call. The API uses PATCH semantics, meaning only specified fields are updated; unspecified fields remain unchanged. IMPORTANT: When updating multiple records in a batch, all records must specify the exact same set of field names (e.g., if updating Name and Age for record 1, you must also update Name and Age for record 2). |
| `GRIST_UPDATE_TABLE_METADATA` | Update Table Metadata | Update metadata properties for a table in a Grist document. Currently the main updatable property is 'onDemand' which controls lazy loading of table data. Use List Tables to find valid table IDs first. |
| `GRIST_UPDATE_WEBHOOK` | Update Webhook | Update an existing webhook configuration for a Grist document. Use to modify webhook settings such as URL, event types, enabled status, or target table. Requires valid document ID (from GRIST_LIST_WORKSPACES) and webhook ID (from GRIST_LIST_WEBHOOKS). Only provided fields will be updated; omitted fields remain unchanged. |
| `GRIST_UPLOAD_ATTACHMENT` | Upload Attachment | Upload one or more file attachments to a Grist document. Returns attachment IDs that can be used to link files to records in Attachments-type columns. First use GRIST_LIST_WORKSPACES to get a valid document ID. |

## Supported Triggers

None listed.

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

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

### 1. Getting API Keys for OpenAI, Composio, and Grist

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 Grist 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, grist)
- 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 Grist 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=["grist"],
    )

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

  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 Grist 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 Grist
```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 Grist, 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=["grist"],
    )

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

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

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

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [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.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Grist MCP?

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

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

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

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