Integrating LangGraph with MySQL Data via CData Connect AI

LangGraph is a framework for building and visualizing intelligent, graph-based AI workflows that combine reasoning models (LLMs) with tool integrations and data operations. By integrating it with the CData Connect AI, you can enable agents to securely access, query, and act on live enterprise data in real-time via a standardized toolset.

CData Connect AI is a managed MCP-platform that allows you to expose your data sources (such as MySQL) through the Model Context Protocol (MCP). This means your AI agents can work with metadata, catalogs, tables, and SQL-enabled data access from hundreds of data sources, without complex ETL or custom integrations.

This article explores how to register the MCP endpoint in LangGraph, configure data source connectivity via CData Connect AI, and build a workflow that queries and visualizes live data (for example, MySQL objects) on demand. It demonstrates how to use the built-in MCP toolset (getCatalogs, getSchemas, getTables, queryData, etc.) to enable natural-language agents to interact with your enterprise data securely and interactively.

Prerequisites

• An account in CData Connect AI.
• Python version 3.10 or higher, to install the LangGraph packages.
• Generate and save an OpenAI API key.
• Install Visual Studio Code in your system.
• Obtain and save the LangGraph API key from LangGraph.

Step 1: Configure MySQL Connectivity for LangGraph

Before LangGraph can access MySQL, a MySQL connection must be created in CData Connect AI. This connection is then exposed to LangGraph through the remote MCP server.

1. Log in to Connect AI click Sources, and then click + Add Connection 👁 Adding a Connection
   
2. From the available data sources, choose MySQL 👁 Selecting a data source
   
3. Enter the necessary authentication properties to connect to MySQL.

   The CData Provider supports connecting to on-premises and cloud-hosted versions of MySQL such as Amazon RDS for MySQL, Google Cloud SQL for MySQL, Azure Database for MySQL, or Oracle MySQL HeatWave. The Server and Port properties must be set to a MySQL server. If IntegratedSecurity is set to false, then User and Password must be set to valid user credentials. Optionally, Database can be set to connect to a specific database. If not set, tables from all databases will be returned.

   SSH Connectivity for MySQL

   You can use SSH (Secure Shell) to authenticate with MySQL, whether the instance is hosted on-premises or in supported cloud environments. SSH authentication ensures that access is encrypted (as compared to direct network connections).

   SSH Connections to MySQL in Password Auth Mode

   To connect to MySQL via SSH in Password Auth mode, set the following connection properties:

   • User: MySQL User name
   • Password: MySQL Password
   • Database: MySQL database name
   • Server: MySQL Server name
   • Port: MySQL port number like 3306
   • UserSSH: "true"
   • SSHAuthMode: "Password"
   • SSHPort: SSH Port number
   • SSHServer: SSH Server name
   • SSHUser: SSH User name
   • SSHPassword: SSH Password

   SSH Connections to MySQL in Public Key Auth Mode

   To connect to MySQL via SSH in Password Auth mode, set the following connection properties:

   • User: MySQL User name
   • Password: MySQL Password
   • Database: MySQL database name
   • Server: MySQL Server name
   • Port: MySQL port number like 3306
   • UserSSH: "true"
   • SSHAuthMode: "Public_Key"
   • SSHPort: SSH Port number
   • SSHServer: SSH Server name
   • SSHUser: SSH User name
   • SSHClientCret: the path for the public key certificate file
   👁 Configuring a connection (Salesforce is shown)
   
4. Click Save & Test
5. Once authenticated, open the Permissions tab in the MySQL connection and configure user-based permissions as required 👁 Updating permissions
   

Generate a Personal Access Token (PAT)

LangGraph authenticates to Connect AI using an account email and a Personal Access Token (PAT). Creating separate PATs for each integration is recommended to maintain granular access control.

1. In Connect AI, select the Gear icon in the top-right to open Settings
2. Under Access Tokens, select Create PAT
3. Provide a descriptive name for the token and select Create 👁 Creating a new PAT
   
4. Copy the token and store it securely. The PAT will only be visible during creation

With the MySQL connection configured and a PAT generated, LangGraph is prepared to connect to MySQL data through the CData MCP server.

Step 2: Set up your development environment

Set up your project directory and install the required dependencies to connect LangGraph with CData Connect AI and use OpenAI LLM for reasoning. This setup enables LangGraph to call the MySQL MCP server tools exposed by Connect AI while OpenAI processes the natural language reasoning.

1. Create a new folder for your LangGraph project:

   mkdir LangGraph cd LangGraph

2. Install the required Python packages:

   pip install langgraph langchain-openai langchain-mcp-adapters python-dotenv "langgraph-cli[inmem]"

3. Ensure you have Python 3.10+ and a valid OpenAI API key configured in your environment.

Step 3: Configure the MCP connection environment variables

LangGraph uses environment variables to connect to the CData Connect AI and define the API credentials and configuration settings. Store these credentials in a .env file to keep them secure and reusable. LangGraph automatically reads this file at runtime, so the script can authenticate and communicate with the MCP server without hardcoding sensitive information.

1. Create a new file named .env in your project directory.
2. Add the following environment variables to define your LangGraph, CData Connect AI, and OpenAI configuration:

   # LangSmith (Optional) 
   LANGSMITH_API_KEY=lsv2_pt_xxxx #LangSmith API Key
   LANGCHAIN_TRACING_V2=true 
   LANGCHAIN_PROJECT=LangGraph-Demo 
   
   # MCP Configuration 
   MCP_BASE_URL=https://mcp.cloud.cdata.com/mcp #MCP Server URL
   MCP_AUTH=base64encoded(EMAIL:PAT) #Base64 encoded Connect AI Email:PAT
   OPENAI_API_KEY=sk-proj-xxxx 
   

3. Save the file. LangGraph uses these values to authenticate with the CData Connect AI MySQL MCP server to connect with the MySQL data and initialize the OpenAI model for reasoning.

Note: You can generate the Base64-encoded authorization string using any online Base64 encoder, such as Base64 encoding tool. Encode your CData Connect AI username and PAT (obtained in the prerequisites).

Step 4: Create the LangGraph agent script

In this step, you need to create a Python script that connects LangGraph to your CData Connect AI MCP server. The script retrieves the available MCP tools, such as getCatalogs, getSchemas, and queryData, builds a LangGraph workflow, and runs a natural language prompt against your connected MySQL data.

The workflow uses the MCP to securely retrieve live MySQL data from Connect AI and uses OpenAI GPT-4o to interpret and reason over that data. You also expose the graph so you can visualize it later in LangGraph Studio.

Create the file

Create a new Python file named test.py inside your LangGraph project folder.

Add the following code

Use the following script into test.py:

import asyncio
import os
import operator
from typing_extensions import TypedDict, Annotated
from dotenv import load_dotenv

from langgraph.graph import StateGraph, START, END
from langchain.agents import create_agent
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langchain_core.messages import BaseMessage, HumanMessage

# Load environment variables
load_dotenv()

# Define the agent state
class AgentState(TypedDict):
 messages: Annotated[list[BaseMessage], operator.add]

# Define the async agent logic
async def run_agent(user_prompt: str) -> str:
 MCP_BASE_URL = os.getenv("MCP_BASE_URL")
 MCP_AUTH = os.getenv("MCP_AUTH")
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

 print("Connecting to the MCP server...")
 mcp_client = MultiServerMCPClient(
 connections={
 "default": {
 "transport": "streamable_http",
 "url": MCP_BASE_URL,
 "headers": {"Authorization": f"Basic {MCP_AUTH}"} if MCP_AUTH else {},
 }
 }
 )

 print("Loading available MCP tools...")
 all_mcp_tools = await mcp_client.get_tools()
 print(f"Loaded tools: {[tool.name for tool in all_mcp_tools]}")

 # Initialize the LLM
 llm = ChatOpenAI(model="gpt-4o", temperature=0.2, api_key=OPENAI_API_KEY)

 print("Creating the LangGraph agent...")
 agent = create_agent(
 model=llm,
 tools=all_mcp_tools,
 system_prompt="You are a helpful assistant. Use tools when needed."
 )

 # Build the workflow graph
 builder = StateGraph(AgentState)
 builder.add_node("agent", agent)
 builder.add_edge(START, "agent")
 builder.add_edge("agent", END)
 graph_instance = builder.compile()

 print(f"Processing user query: {user_prompt}\n")
 initial_state = {"messages": [HumanMessage(content=user_prompt)]}
 result = await graph_instance.ainvoke(initial_state)
 print(f"Agent Response:\n{result['messages'][-1].content}")

# Expose the graph for visualization
builder = StateGraph(AgentState)
builder.add_node(
 "agent",
 create_agent(
 model=ChatOpenAI(model="gpt-4o", temperature=0.2, api_key=os.getenv("OPENAI_API_KEY")),
 tools=[],
 system_prompt="You are a helpful assistant."
 )
)
builder.add_edge(START, "agent")
builder.add_edge("agent", END)
graph = builder.compile()

if __name__ == "__main__":
 import argparse
 parser = argparse.ArgumentParser()
 parser.add_argument("--serve", action="store_true", help="Run visualization server")
 args = parser.parse_args()

 if args.serve:
 print("To visualize the graph, run:")
 print("langgraph dev")
 else:
 asyncio.run(run_agent("List the first 2 catalogs available"))

Step 5: Configure the LangGraph project

Configure the LangGraph project so the CLI recognizes the workflow graph and environment settings. Create a configuration file that registers the graph for use in LangGraph Studio or during local visualization runs.

Create the configuration file

Create a new file named langgraph.json in your project directory.

Add the following configuration

Use the content below in the langgraph.json file:

{
 "dependencies": ["."],
 "graphs": {
 "agent": "./test.py:graph"
 },
 "env": ".env"
}

Step 6: Prompt MySQL using LangGraph (via Connect AI)

Run the LangGraph development server to view and interact with your workflow in LangGraph Studio. This allows direct visualization of how the agent processes prompts, invokes tools, and retrieves MySQL data through the MCP server.

Start the LangGraph development server

Open a terminal in your project directory and run:

langgraph dev

👁 Start the LangGraph development server

Access the Studio interface

After the server starts, LangGraph launches a local API and provides a link to the Studio UI:

https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

Ideally, the link opens automatically when the command is run. If not, open this link in your browser to load the LangGraph Studio dashboard.

Interact with the agent

In the Studio interface, enter a natural language prompt such as:

Show all MySQL tables available in my catalog

LangGraph displays a real-time visualization of the agent's reasoning flow, showing how it interprets the prompt, calls the appropriate MCP tools, and retrieves live data from MySQL.

👁 Query and visualize the MySQL data
👁 Query and visualize the MySQL data (contd.)

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!