How to integrate Snowflake MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Snowflake Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Snowflake to CrewAI using the Composio tool router. By the end, you'll have a working Snowflake agent that can run a sql query to list today's new users, cancel a long-running data import statement, show all unresolved incidents in snowflake, list upcoming scheduled maintenances for the week through natural language commands.

This guide will help you understand how to give your CrewAI 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.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Snowflake connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Snowflake
  • Build a conversational loop where your agent can execute Snowflake operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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 cloud data warehouse, so your agent can run complex SQL queries, monitor system health, check scheduled maintenances, and manage incidents seamlessly—no manual intervention needed.

  • Automated SQL execution and data retrieval: Direct your agent to execute SQL statements and instantly fetch query results from your data warehouse.
  • Query management and cancellation: Have your agent monitor and cancel long-running or stuck SQL statements to keep your workflows running smoothly.
  • Maintenance and system status monitoring: Let your agent check for active, upcoming, or completed scheduled maintenances and get real-time updates on system components.
  • Incident detection and reporting: Enable your agent to retrieve unresolved incidents and receive summaries of any issues currently affecting your Snowflake environment.
  • Integration metadata access: Fetch details about catalog integrations and system status rollups so your agent can keep tabs on the overall health of your Snowflake setup.

Supported Tools & Triggers

Tools
Cancel Statement ExecutionCancels the execution of a running SQL statement.
Check Statement StatusRetrieves the status of a previously submitted SQL statement.
Execute SQLTool to execute a SQL statement and return the resulting data.
Fetch Catalog IntegrationFetches details of a specific catalog integration.
Get Active Scheduled MaintenancesRetrieves a list of any active scheduled maintenances currently in the In Progress or Verifying state.
Get All Scheduled MaintenancesRetrieves a list of the 50 most recent scheduled maintenances, including those in the Completed state.
Get Component StatusRetrieves the status of individual components, each listed with its current status.
Get Status RollupRetrieves the status rollup for the entire page, including indicators and human-readable descriptions of the blended component status.
Get Status SummaryRetrieves a summary of the status page, including status indicators, component statuses, unresolved incidents, and upcoming or in-progress scheduled maintenances.
Get Unresolved IncidentsRetrieves a list of any unresolved incidents currently in the Investigating, Identified, or Monitoring state.
Get Upcoming Scheduled MaintenancesRetrieves a list of any upcoming scheduled maintenances still in the Scheduled state.
Show DatabasesLists all databases for which you have access privileges.
Show SchemasLists all schemas for which you have access privileges.
Show TablesLists all tables for which you have access privileges.
Submit SQL StatementSubmits a SQL statement for execution.

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 and API key
  • A Snowflake connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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 crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Snowflake via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

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_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Snowflake MCP URL

Create a Composio Tool Router session for Snowflake

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["snowflake"],
)
url = session.mcp.url
What's happening:
  • You create a Snowflake only session through Composio
  • Composio returns an MCP HTTP URL that exposes Snowflake tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Snowflake Assistant",
    goal="Help users interact with Snowflake through natural language commands",
    backstory=(
        "You are an expert assistant with access to Snowflake tools. "
        "You can perform various Snowflake operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Snowflake MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Snowflake operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Snowflake related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_snowflake_agent.py

Complete Code

Here's the complete code to get you started with Snowflake and CrewAI:

python
# file: crewai_snowflake_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Snowflake session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["snowflake"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Snowflake assistant agent
    toolkit_agent = Agent(
        role="Snowflake Assistant",
        goal="Help users interact with Snowflake through natural language commands",
        backstory=(
            "You are an expert assistant with access to Snowflake tools. "
            "You can perform various Snowflake operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Snowflake operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Snowflake related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Snowflake through Composio's Tool Router. The agent can perform Snowflake operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Snowflake MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Snowflake MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Snowflake MCP with Claude Agent SDK

Google ADK

Google ADK

Use Snowflake MCP with Google ADK

LangChain

LangChain

Use Snowflake MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Snowflake MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Snowflake MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Snowflake MCP with LlamaIndex

FAQ

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

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.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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.

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

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.

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 Snowflake 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