SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Snowflake MCP with Pydantic AI

Connect Pydantic AI to Snowflake MCP. Run a sql query to list today's new users, cancel a long-running data import statement, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Snowflake logoSnowflake
Oauth2

Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds.

16 Tools

Introduction

This guide walks you through connecting Snowflake to Pydantic AI using the Composio tool router. By the end, you'll have a working Snowflake agent that can run SQL statements, check or cancel running queries, list databases and schemas, browse tables, and monitor Snowflake service status through natural language commands.

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

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

Also integrate Snowflake with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexKimi CodeGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

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 Snowflake
  • 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 Snowflake 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 Snowflake MCP server, and what's possible with it?

The Snowflake MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Snowflake account. It provides structured and secure access to your data warehouse and Snowflake service status, so your agent can execute SQL, explore databases and tables, track or cancel statements, inspect catalog integrations, and monitor incidents and maintenance on your behalf.

  • SQL execution and analysis: Have your agent run SQL statements in Snowflake and retrieve the results for analysis.
  • Database structure discovery: Let the agent list the databases, schemas, and tables your account can access.
  • Statement monitoring and control: Direct your agent to check the status and results of submitted SQL statements or cancel a running statement.
  • Warehouse and catalog administration: Instruct your agent to review the configuration of a catalog integration or permanently drop a warehouse when needed.
  • Service health monitoring: Have your agent check Snowflake component status, unresolved incidents, and active, recent, or upcoming scheduled maintenance.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step09 STEPS
1

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
2

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.
3

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 Snowflake
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

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
5

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 Snowflake
  • MCPServerStreamableHTTP connects to the Snowflake MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

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 Snowflake
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["snowflake"],
    )
    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 Snowflake 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
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
snowflake_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[snowflake_mcp],
    instructions=(
        "You are a Snowflake assistant. Use Snowflake tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Snowflake endpoint
  • The agent uses GPT-5 to interpret user commands and perform Snowflake operations
  • The instructions field defines the agent's role and behavior
8

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 Snowflake.\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
  • Snowflake API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

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 Snowflake 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 Snowflake
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["snowflake"],
    )
    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
    snowflake_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[snowflake_mcp],
        instructions=(
            "You are a Snowflake assistant. Use Snowflake 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 Snowflake.\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 Snowflake through Composio's Tool Router. With this setup, your agent can perform real Snowflake 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 + Snowflake for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Snowflake action and event your agent gets out of the box.

Cancel Statement Execution

Cancels the execution of a running SQL statement.

Check Statement Status

Checks a submitted SQL statement by handle and retrieves results for a completed statement, optionally for a specified partition.

Drop Warehouse

Drops a Snowflake warehouse by its case-sensitive name.

Execute SQL

Submits SQL statements to Snowflake, including SELECT, DDL, and DML.

Fetch Catalog Integration

Retrieves detailed configuration and metadata for a specific catalog integration.

Get Active Scheduled Maintenances

Retrieves a list of any active scheduled maintenances currently in the In Progress or Verifying state.

Get All Scheduled Maintenances

Retrieves up to 10 of the 50 most recent scheduled maintenances from Snowflake's status page, including completed events.

Get Component Status

Retrieves the status of individual components, each listed with its current status.

Get Status Rollup

Retrieves the status rollup for the entire page, including indicators and human-readable descriptions of the blended component status.

Get Status Summary

Retrieves Snowflake's public status summary, including overall status, component statuses, unresolved incidents, and upcoming or in-progress maintenance.

Get Unresolved Incidents

Retrieves a list of any unresolved incidents from the Snowflake status page.

Get Upcoming Scheduled Maintenances

Retrieves upcoming scheduled maintenances from Snowflake's public status page.

Show Databases

Lists all databases for which you have access privileges.

Show Schemas

Lists all schemas for which you have access privileges.

Show Tables

Lists accessible Snowflake tables in the requested scope, with metadata, filters, and optional dropped-table history.

Validate Credential

Checks Snowflake credentials by submitting a lightweight session query, useful before running other account operations.

FRAMEWORKS

How to build Snowflake MCP Agent with another framework

Claude Code logo

Claude Code

Use Snowflake MCP with Claude Code

Cursor logo

Cursor

Use Snowflake MCP with Cursor

ChatGPT logo

ChatGPT

Use Snowflake MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Snowflake MCP with Claude Cowork

Antigravity logo

Antigravity

Use Snowflake MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Snowflake MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Snowflake MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Snowflake MCP with Grok Bot

Muse logo

Muse

Use Snowflake MCP with Muse

Codex logo

Codex

Use Snowflake MCP with Codex

Kimi Code logo

Kimi Code

Use Snowflake MCP with Kimi Code

Grok Build logo

Grok Build

Use Snowflake MCP with Grok Build

VS Code logo

VS Code

Use Snowflake MCP with VS Code

OpenCode logo

OpenCode

Use Snowflake MCP with OpenCode

OpenClaw logo

OpenClaw

Use Snowflake MCP with OpenClaw

Hermes logo

Hermes

Use Snowflake MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Snowflake MCP with Atomic Agent

CLI logo

CLI

Use Snowflake MCP with CLI

Google ADK logo

Google ADK

Use Snowflake MCP with Google ADK

LangChain logo

LangChain

Use Snowflake MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Snowflake MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Snowflake MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Snowflake MCP with LlamaIndex

CrewAI logo

CrewAI

Use Snowflake MCP with CrewAI

AutoGen logo

AutoGen

Use Snowflake MCP with AutoGen

FAQ

Frequently asked questions

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

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 Snowflake tools.

Yes, absolutely. You can configure which Snowflake 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.

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 Snowflake data and credentials are handled as safely as possible.

Start with Snowflake.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Snowflake tool your agent needs.Free to start.

Start building