How to integrate Grist MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Grist Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Grist to the OpenAI Agents SDK 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have a working Grist agent that can add new sales data to q2 table, create a document for project planning, delete outdated rows from inventory sheet, remove email column from contacts table through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK 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.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Grist
  • Configure an AI agent that can use Grist as a tool
  • Run a live chat session where you can ask the agent to perform Grist operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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 & Triggers

Tools
Add RecordsTool to add records to a specified table in a Grist document.
Create DocumentTool to create a document in a workspace.
Create SCIM UserTool to create a new SCIM user.
Create TableTool to create tables in a document.
Create Document WebhookTool to create a new webhook for a specified document.
Delete AttachmentTool to delete a specified attachment from a Grist document.
Delete ColumnTool to delete a column from a Grist document table.
Delete Grist Table RecordsTool to delete records from a specified Grist table.
Delete SCIM UserTool to delete a specified user via SCIM.
Delete WebhookTool to delete a webhook from a Grist document.
Download All Attachments ArchiveTool to download all attachments from a Grist document as a .
Download AttachmentTool to download the binary data of an attachment.
Download Grist Attachment ContentTool to download the raw bytes of an attachment.
Fetch Column MetadataTool to fetch metadata for a specific column in a Grist document table.
Fetch Document MetadataTool to fetch metadata for a specified Grist document.
Fetch Table MetadataTool to retrieve metadata for a specified table in a Grist document.
Get Org AccessTool to fetch org access details.
Get UsersTool to retrieve a list of users via SCIM v2.
List AttachmentsTool to list all attachments in a Grist document.
List ColumnsTool to list all columns in a specified Grist table.
List OrganizationsTool to list all organizations accessible to the authenticated user.
List RecordsTool to retrieve records from a specified table within a Grist document.
List TablesTool to list all tables within a specified document.
List WebhooksTool to list webhooks configured for a document.
List WorkspacesTool to list all workspaces and documents accessible to the authenticated user on the current site.
Run SQL QueryTool to execute a read-only SQL SELECT query on a Grist document.
Update Column MetadataTool to update metadata for one or more columns in a Grist document table.
Update Document MetadataTool to update metadata for a specified Grist document.
Update RecordsTool to update records in a specified table within a document.
Update Table MetadataTool to update metadata for a specified table.
Update WebhookTool to update an existing webhook for a specified document.
Upload AttachmentTool to upload one or more attachments to a Grist document.

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:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Grist project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Grist.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Grist Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["grist"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only grist.
  • The router checks the user's Grist connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Grist.
  • This approach keeps things lightweight and lets the agent request Grist tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Grist. "
        "Help users perform Grist operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Grist and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Grist operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Grist.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Grist and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["grist"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Grist. "
        "Help users perform Grist operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Grist MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Grist.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Grist MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Grist MCP with Claude Agent SDK

Google ADK

Google ADK

Use Grist MCP with Google ADK

LangChain

LangChain

Use Grist MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Grist MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Grist MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Grist MCP with LlamaIndex

CrewAI

CrewAI

Use Grist MCP with CrewAI

FAQ

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 OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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.

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