Integrating Dataiku with PingOne Data via CData Connect AI

Dataiku is a collaborative data science and AI platform that enables teams to design, deploy, and manage machine learning and generative AI projects within a governed environment. It's Agent and GenAI framework allows users to build intelligent agents that can analyze, generate, and act on data through custom workflows and model orchestration.

By integrating Dataiku with CData Connect AI through the built-in MCP (Model Context Protocol) Server, these agents gain secure, real-time access to live PingOne data. The integration bridges Dataiku's agent execution environment with CData's governed enterprise connectivity layer, allowing every query or instruction to run safely against authorized data sources without manual exports or staging.

This article demonstrates how to configure PingOne connectivity in Connect AI, prepare a Python code environment in Dataiku with MCP support, and create an agent that queries and interacts with live PingOne data directly from within Dataiku.

Step 1: Configure PingOne Connectivity for Dataiku

Connectivity to PingOne from Dataiku is made possible through CData Connect AI's Remote MCP Server. To interact with PingOne data from Dataiku, you start by creating and configuring a PingOne connection in CData Connect AI.

1. Log into Connect AI, click Sources, then click Add Connection

2. Select "PingOne" from the Add Connection panel

3. 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.

   
4. Click Save & Test
5. Open the Permissions tab and set user-based permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Dataiku. It is best practice to create a separate PAT for each integration to maintain granular access control

1. Click the gear icon () at the top right of the Connect AI app to open Settings
2. On the Settings page, go to the Access Tokens section and click Create PAT
3. Give the PAT a descriptive name and click Create

4. Copy the token when displayed and store it securely. It will not be shown again

With the PingOne connection configured and a PAT generated, Dataiku can now connect to PingOne data through the Connect AI.

Step 2: Prepare Dataiku and the Code Environment

A dedicated python code environment in Dataiku provides the runtime support needed for MCP-based communication. To enable Dataiku Agents to connect to CData Connect AI, create a Python environment and install the MCP client dependencies required for agent-to-server interaction.

1. In Dataiku Cloud, open Code Envs

2. Click Add a code env to open the DSS settings window

3. In DSS, click New Python env. Name it (for example, MCP_Package) and choose Python 3.10 (3.10 to 3.13 supported)

4. Open Packages to install and add the following pip packages:
• httpx
• anyio
• langchain-mcp-adapters

5. Open Containerized execution and under Container runtime additions select Agent tool MCP servers support

6. Check Rebuild env and click Save and update to install packages
7. Back in Dataiku Cloud, open Overview and click Open instance

8. Click + New project and select Blank project. Name the project

Step 3: Create a Dataiku Agent and connect to the MCP server

The Dataiku Agent serves as the bridge between the Dataiku workspace and Connect AI. To enable this connection, create a custom code-based agent, assign it the configured Python environment, and embed your Connect AI credentials to allow the agent to query and interact with live PingOne data.

1. Go to Agents & GenAI Models and click Create your first agent

2. Choose Code agent, name it, and for Agent version select Asynchronous agent without streaming

3. From the tab above select Settings. In Code env selection set Default Python code env to the environment you created (for example, MCP_Package)

4. Return to the Agent Design tab and paste the following code. Replace EMAIL, and PAT with your values

import os
import base64
from typing import Dict, Any, List
 
from dataiku.llm.python import BaseLLM
from langchain_mcp_adapters.client import MultiServerMCPClient
 
# ---------- Persistent MCP client (cached between calls) ----------
_MCP_CLIENT = None
 
def _get_mcp_client() -> MultiServerMCPClient:
    """Create (or reuse) a MultiServerMCPClient to CData Cloud MCP."""
    global _MCP_CLIENT
    if _MCP_CLIENT is not None:
        return _MCP_CLIENT
 
    # Set creds via env/project variables ideally
    EMAIL = os.getenv("CDATA_EMAIL", "YOUR_EMAIL") 
    PAT   = os.getenv("CDATA_PAT",   "YOUR_PAT")        
    BASE_URL = "https://mcp.cloud.cdata.com/mcp"
 
    if not EMAIL or PAT == "YOUR_PAT":
        raise ValueError("Set CDATA_EMAIL and CDATA_PAT as env variables or inline in the code.")
 
    token = base64.b64encode(f"{EMAIL}:{PAT}".encode()).decode()
    headers = {"Authorization": f"Basic {token}"}
 
    _MCP_CLIENT = MultiServerMCPClient(
        connections={
            "cdata": {
                "transport": "streamable_http",
                "url": BASE_URL,
                "headers": headers,
            }
        }
    )
    return _MCP_CLIENT
 
 
def _pick_tool(tools, names: List[str]):
    L = [n.lower() for n in names]
    return next((t for t in tools if t.name.lower() in L), None)
 
 
async def _route(prompt: str) -> str:
    """
    Simple intent router:
      - 'list connections' / 'list catalogs' -> getCatalogs
      - 'sql: ...' or 'query: ...' -> queryData
      - otherwise -> help text
    """
    client = _get_mcp_client()
    tools = await client.get_tools()
 
    p = prompt.strip()
    low = p.lower()
 
    # 1) List connections (catalogs)
    if "list connections" in low or "list catalogs" in low:
        t = _pick_tool(tools, ["getCatalogs", "listCatalogs"])
        if not t:
            return "No 'getCatalogs' tool found on the MCP server."
        res = await t.ainvoke({})
        return str(res)[:4000]
 
    # 2) Run SQL
    if low.startswith("sql:") or low.startswith("query:"):
        sql = p.split(":", 1)[1].strip()
        t = _pick_tool(tools, ["queryData", "sqlQuery", "runQuery", "query"])
        if not t:
            return "No query-capable tool (queryData/sqlQuery) found on the MCP server."
        try:
            res = await t.ainvoke({"query": sql})
            return str(res)[:4000]
        except Exception as e:
            return f"Query failed: {e}"
 
    # 3) Help
    return (
        "Connected to CData MCP

"
        "Say **'list connections'** to view available sources, or run a SQL like:
"
        "  sql: SELECT * FROM [Salesforce1].[SYS].[Connections] LIMIT 5

"
        "Remember to use bracket quoting for catalog/schema/table names."
    )
 
 
class MyLLM(BaseLLM):
    async def aprocess(self, query: Dict[str, Any], settings: Dict[str, Any], trace: Any):
        # Extract last user message from the Quick Test payload
        prompt = ""
        try:
            prompt = (query.get("messages") or [])[-1].get("content", "")
        except Exception:
            prompt = ""
 
        try:
            reply = await _route(prompt)
        except Exception as e:
            reply = f"Error: {e}"
 
        # The template expects a dict with a 'text' key
        return {"text": reply}

Run a Quick Test

1. Open Quick Test on the right side panel
2. Paste the JSON code and click Run test

{
   "messages": [
      {
         "role": "user",
         "content": "list connections"
      }
   ],
   "context": {}
}

Chat with your Agent

Switch to the Chat tab and try prompting like, "List all connections". The chat output will show a list of connection catalogs.



Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources from your AI agents, try CData Connect AI today.