Integrating LlamaIndex with PingOne Data via CData Connect AI

Leverage the CData Connect AI Remote MCP Server to enable LlamaIndex ReAct agents to securely access and act on PingOne data in real time.

LlamaIndex is a data framework for building LLM applications — agents, RAG pipelines, and structured workflows that reason over external data. By integrating LlamaIndex with CData Connect AI through the built-in MCP Server, your agents can discover and query live PingOne data as native tools without writing custom connectors.

CData Connect AI offers a secure, low-code environment to connect PingOne and other data sources, removing the need for complex ETL and enabling seamless automation across business applications with live data.

This article outlines how to configure PingOne connectivity in CData Connect AI, register the MCP server with LlamaIndex, and build a ReAct agent that queries PingOne data in real time.

Prerequisites

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

Step 1: Configure PingOne Connectivity for LlamaIndex

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

Log in to Connect AI, click Sources, and then click + Add Connection
From the available data sources, choose PingOne
Enter the necessary authentication properties to connect to PingOne
To connect to PingOne, configure these properties:
- Region: The region where the data for your PingOne organization is being hosted.
- AuthScheme: The type of authentication to use when connecting to PingOne.
- Either WorkerAppEnvironmentId (required when using the default PingOne domain) or AuthorizationServerURL, configured as described below.
Configuring WorkerAppEnvironmentId

WorkerAppEnvironmentId is the ID of the PingOne environment in which your Worker application resides. This parameter is used only when the environment is using the default PingOne domain (auth.pingone). It is configured after you have created the custom OAuth application you will use to authenticate to PingOne, as described in Creating a Custom OAuth Application in the Help documentation.

First, find the value for this property:
1. From the home page of your PingOne organization, move to the navigation sidebar and click Environments.
2. Find the environment in which you have created your custom OAuth/Worker application (usually Administrators), and click Manage Environment. The environment's home page displays.
3. In the environment's home page navigation sidebar, click Applications.
4. Find your OAuth or Worker application details in the list.
5. Copy the value in the Environment ID field. It should look similar to:
```
WorkerAppEnvironmentId='11e96fc7-aa4d-4a60-8196-9acf91424eca'
```
Now set WorkerAppEnvironmentId to the value of the Environment ID field.

Configuring AuthorizationServerURL

AuthorizationServerURL is the base URL of the PingOne authorization server for the environment where your application is located. This property is only used when you have set up a custom domain for the environment, as described in the PingOne platform API documentation. See Custom Domains.

Authenticating to PingOne with OAuth

PingOne supports both OAuth and OAuthClient authentication. In addition to performing the configuration steps described above, there are two more steps to complete to support OAuth or OAuthCliet authentication:
- Create and configure a custom OAuth application, as described in Creating a Custom OAuth Application in the Help documentation.
- To ensure that the driver can access the entities in Data Model, confirm that you have configured the correct roles for the admin user/worker application you will be using, as described in Administrator Roles in the Help documentation.
- Set the appropriate properties for the authscheme and authflow of your choice, as described in the following subsections.
OAuth (Authorization Code grant)

Set AuthScheme to OAuth.

Desktop Applications

Get and Refresh the OAuth Access Token

After setting the following, you are ready to connect:
- InitiateOAuth: GETANDREFRESH. To avoid the need to repeat the OAuth exchange and manually setting the OAuthAccessToken each time you connect, use InitiateOAuth.
- OAuthClientId: The Client ID you obtained when you created your custom OAuth application.
- OAuthClientSecret: The Client Secret you obtained when you created your custom OAuth application.
- CallbackURL: The redirect URI you defined when you registered your custom OAuth application. For example: https://localhost:3333
When you connect, the driver opens PingOne's OAuth endpoint in your default browser. Log in and grant permissions to the application. The driver then completes the OAuth process:
1. The driver obtains an access token from PingOne and uses it to request data.
2. The OAuth values are saved in the location specified in OAuthSettingsLocation, to be persisted across connections.
The driver refreshes the access token automatically when it expires.

For other OAuth methods, including Web Applications, Headless Machines, or Client Credentials Grant, refer to the Help documentation.
Click Save & Test
Once authenticated, open the Permissions tab in the PingOne connection and configure user-based permissions as required

Generate a Personal Access Token (PAT)

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

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

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

Step 2: Connect to the MCP server in LlamaIndex

To connect LlamaIndex with CData Connect AI Remote MCP Server and use OpenAI for reasoning, configure your MCP server endpoint and authentication in a

config.py

file. These values let LlamaIndex’s MCP tool spec call the MCP server tools, while OpenAI handles the natural language reasoning.

Create a folder for the LlamaIndex MCP project
Create two Python files within the folder:
```
config.py
```
and
```
llamaindex_agent.py
```
In
```
config.py
```
, define your MCP server URL and your Base64-encoded CData Connect AI email and PAT (obtained in the prerequisites):
```
class Config:

      MCP_BASE_URL = "https://mcp.cloud.cdata.com/mcp"   # MCP Server URL
      MCP_AUTH     = "base64encoded(EMAIL:PAT)"          # Base64 encoded Connect AI Email:PAT
```
Note: You can create the base64 encoded version of MCP_AUTH using any Base64 encoding tool.

llamaindex_agent.py

, wire up the MCP tool spec and a ReAct agent:


"""
Integrates a LlamaIndex ReAct agent with the CData Connect AI MCP server.
The script discovers MCP tools, wraps them as LlamaIndex tools, and runs an
agent loop driven by OpenAI for reasoning.
"""

import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import ReActAgent
from llama_index.llms.openai import OpenAI
from config import Config

async def main():

    # Initialize the MCP client pointed at Connect AI
    mcp_client = BasicMCPClient(
        Config.MCP_BASE_URL,
        headers={"Authorization": f"Basic {Config.MCP_AUTH}"},
    )

    # Discover tools the MCP server exposes (getCatalogs, queryData, etc.)
    tool_spec = McpToolSpec(client=mcp_client)
    tools = await tool_spec.to_tool_list_async()
    print("Discovered MCP tools:", [t.metadata.name for t in tools])

    # Configure the LLM that drives the ReAct loop
    llm = OpenAI(
        model="gpt-4o",
        temperature=0.2,
        api_key="YOUR_OPENAI_API_KEY",  # https://platform.openai.com/
    )

    # Build the agent with the MCP-backed tools
    agent = ReActAgent(tools=tools, llm=llm)

    user_prompt = "How many tables are available in PingOne1?"  # Change as needed
    print(f"
User prompt: {user_prompt}")

    response = await agent.run(user_prompt)

    print("Agent final response:", response)

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

Step 3: Install the LlamaIndex packages

Since this workflow uses LlamaIndex together with the CData Connect AI MCP server and OpenAI for reasoning, install the required Python packages.

Run the following command in your project terminal:


pip install llama-index llama-index-tools-mcp llama-index-llms-openai

Step 4: Prompt PingOne using LlamaIndex (via the MCP server)

When the installation finishes, run
```
python llamaindex_agent.py
```
to execute the script
The script connects to the MCP server and discovers the CData Connect AI MCP tools available for querying your connected data
Supply a prompt (e.g., "How many tables are available in PingOne?")
The agent reasons over the available tools, calls
```
queryData
```
against PingOne, and responds with the result

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!

Ready to get started?

Learn more about CData Connect AI or sign up for free trial access:

Free Trial

CData is the data layer that makes AI work in production—live connectivity and replication across hundreds of the most critical enterprise sources, semantic context, and built-in governance. Powering AI for Databricks, Microsoft, Google, Palantir, and 10,000+ customers worldwide.

Integrating LlamaIndex with PingOne Data via CData Connect AI

Prerequisites

Step 1: Configure PingOne Connectivity for LlamaIndex

Configuring WorkerAppEnvironmentId

Configuring AuthorizationServerURL

Authenticating to PingOne with OAuth

OAuth (Authorization Code grant)

Desktop Applications