How to integrate Gigasheet MCP with Pydantic AI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Gigasheet Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Gigasheet to Pydantic AI using the Composio tool router. By the end, you'll have a working Gigasheet agent that can list all columns in my sales dataset, download export url for last week's data, apply saved filter to monthly report sheet, show all filter templates in my workspace through natural language commands.

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

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

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Gigasheet
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Gigasheet workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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

The Gigasheet MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gigasheet account. It provides structured and secure access to your big data spreadsheets, so your agent can perform actions like retrieving datasets, applying filters, exporting data, managing sheets, and integrating with connector sources on your behalf.

  • Dataset retrieval and inspection: Instantly fetch metadata or details for any dataset or sheet, such as column names, types, and structure, so you can quickly understand and analyze your data.
  • Automated data export and download: Direct your agent to initiate data exports and retrieve download links for processed datasets, streamlining big data extraction directly to your tools or workflows.
  • Smart filtering and template application: Apply saved filter templates to sheets or retrieve available filter templates, enabling rapid, repeatable data curation without manual setup.
  • Sheet and folder management: Effortlessly delete sheets or folders—including recursive deletions—so you can keep your workspace organized and clutter-free.
  • Connector and integration management: List and manage connector connections to keep all your external data sources in sync with Gigasheet, making data aggregation seamless and automated.

Supported Tools & Triggers

Tools
Delete sheet or folder by handleTool to delete a sheet or folder by handle.
Get Client State Current VersionTool to fetch the current client-state version metadata for a sheet.
Get Connector ConnectionsTool to list connector connections.
Get Dataset by HandleTool to get dataset metadata.
Get Dataset ColumnsTool to list all column metadata (IDs, names, types) for a dataset.
Get Dataset Export Download URLTool to retrieve the download URL for an exported dataset.
Get Dataset ViewsTool to list all views associated with a specific dataset.
Get Docs Formulas FunctionsTool to retrieve all supported formula functions.
Apply Filter Template On SheetTool to fetch a saved filter template's model for a given sheet.
Get Filter TemplatesTool to retrieve all saved filter templates.
Generate New HandleTool to generate a new unique dataset handle.
Get User Autofill InfoTool to fetch autofill info for the authenticated user.
Get Authenticated User InfoTool to fetch the authenticated user's details.
Append Rows to Sheet by NameTool to append rows to a sheet by column names.
Initiate Dataset ExportTool to initiate an export of a dataset.
Insert Blank Row in DatasetTool to insert a blank row with null values into a dataset.
Rename Columns to UniqueTool to rename all columns in a dataset to unique names.
Save Current ViewTool to persist the current view in a Gigasheet dataset.
Get Filtered Row IndexTool to retrieve the filtered-set row index for a given unfiltered row number.
Combine Files by NameTool to combine multiple files by a shared column name.
Export Gigasheet to S3Tool to export Gigasheet data to AWS S3.
Import from S3Tool to import data from AWS S3 into your Gigasheet Library.
Request API AccessTool to request access to the Gigasheet API.
Unroll Delimited ColumnTool to explode a column containing delimited data into multiple rows.
Upload from URLTool to upload data to Gigasheet from a specified URL.
Set Dataset Client State VersionTool to set the client state version of a dataset.
Update cell by column name and rowTool to update a cell in a dataset by specifying column name and row number.
Share fileTool to share a Gigasheet file with specified recipients.
Create/Update Filter TemplateTool to create or update a saved filter template.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Gigasheet
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Gigasheet
  • MCPServerStreamableHTTP connects to the Gigasheet MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Gigasheet
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["gigasheet"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Gigasheet tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
gigasheet_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[gigasheet_mcp],
    instructions=(
        "You are a Gigasheet assistant. Use Gigasheet tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Gigasheet endpoint
  • The agent uses GPT-5 to interpret user commands and perform Gigasheet operations
  • The instructions field defines the agent's role and behavior

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Gigasheet.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Gigasheet API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Gigasheet and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Gigasheet
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["gigasheet"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    gigasheet_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[gigasheet_mcp],
        instructions=(
            "You are a Gigasheet assistant. Use Gigasheet tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Gigasheet.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Gigasheet through Composio's Tool Router. With this setup, your agent can perform real Gigasheet actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Gigasheet for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Gigasheet MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Gigasheet MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Gigasheet MCP with Claude Agent SDK

Google ADK

Google ADK

Use Gigasheet MCP with Google ADK

LangChain

LangChain

Use Gigasheet MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Gigasheet MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Gigasheet MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Gigasheet MCP with LlamaIndex

CrewAI

CrewAI

Use Gigasheet MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Gigasheet MCP?

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

Can I use Tool Router MCP with Pydantic AI?

Yes, you can. Pydantic AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Gigasheet tools.

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

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

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free