Overview

This guide explains how to connect ChatGPT to One Model using the Model Context Protocol (MCP).

Once connected, ChatGPT can securely query governed workforce metrics from One Model and incorporate those results directly into conversational workflows such as analysis, document drafting, reporting, and presentations.

By connecting ChatGPT to One Model via MCP, you can:

• Reduce context switching by querying workforce data directly from ChatGPT
• Stay within your existing workflow while drafting content, writing code, or building presentations
• Combine AI reasoning with trusted One Model metrics to answer complex workforce questions

Terminology & Notes

• In ChatGPT, MCP integrations are referred to as “Apps.” These apps act as connectors to external systems such as One Model. 
• Throughout this guide, the terms App and Connector are used interchangeably, with App reflecting ChatGPT’s interface terminology.
• This guide uses ChatGPT as the reference AI platform. Other MCP-compatible tools may have similar steps but different terminology.

Audience & Prerequisites

This guide is intended for:

• One Model Administrators responsible for setup, configuration and publishing
• Business Users and Analysts with approved access who will connect to and use the app

Part 1: One Model Administrators 

Setup, Configuration, and Publishing

To authorize the connection (the “handshake”) between ChatGPT and your One Model production instance, an Administrator must have the appropriate access levels.

Required Permissions

Ensure your user account is assigned an Application Access Role (AAR) with the following permissions enabled:

• CanAccessOneModelMCP - Allows use of the MCP to communicate with ChatGPT or other external AI tools
• CanConfigureCompany - Grants access to high-level company settings

These permissions are configured via:  Admin > Application Access Role > [Select Role] > Permissions.

Integration Client Configuration

Once permissions are granted, Administrators manage authorized AI integrations through the Integrations page.  This ensures that only approved external tools can access data from your One Model instance.

Step 1: Create a Client Integration in One Model 

• Log into your One Model production instance
• Navigate to Admin > Integration
• Click Create New and select ChatGPT

Approved Client List

For security and compliance, One Model uses a Client Rule Approve List to control which external applications are allowed to connect. 

• You must specify approved client metadata (such as redirect/return URLs)
• This ensures that data is only shared with platforms vetted by your Security and Compliance teams

Pre-configured Templates:  One Model provides pre-configured connector templates for major AI providers. When selecting ChatGPT, Microsoft 365 Copilot, or Claude, required return URLs are auto-populated.

Custom Integrations: For proprietary or unsupported AI tools, select Custom and manually define required metadata fields and allowed values.

Creating the ChatGPT Connector

Step 2: Enable Developer Mode in ChatGPT

1. Log into ChatGPT
2. Open Settings (via your profile icon)

• Navigate to Apps 
• Scroll to Advanced Settings
• Turn Developer Mode on

Step 3: Create a New App

1. Click Create App
2. Configure the One Model connection:
   • App Name: e.g., One Model
   • MCP Server URL: the endpoint for your One Model MCP server
     • Example: https://api.sandbox-dev.pre.mod.io/mcp
     • Be sure to use the correct URL for your environment (production)
   • Authentication Method: OAuth
   • Click Create

Step 4: Accept Permissions

A confirmation screen will display the connector’s capabilities.

• These permissions are defined by One Model
• They are read-only during setup

Click Accept to finalize the connection.

Publishing the Connector

The connector must be published before it can be used by end users.

Step 5: Publish the App 

1. Return to Settings > Apps
2. Locate the newly created One Model app
3. Acknowledge any required trust or security confirmations
4. Click Publish

Important Notes on Publishing & Discoverability

Publishing an app makes it available for use, but visibility may not be immediate.  Please note:

• Publishing does not guarantee immediate discoverability
• Developer Mode affects visibility - Apps created or modified while Developer Mode is enabled may only be visible to the creator
• Republishing may reset trust or visibility - Users may need to re-acknowledge trust or refresh their session
• User sessions are cached - End users may need to refresh the page, switch chats, or log out and back in

Step 6: Verify User Access

If the app does not appear immediately:

1. Turn Developer Mode off
2. Return to the main chat interface
3. Refresh the page or log out and back in

The One Model app should now appear as a selectable tool in ChatGPT.

Step 7: Test the Connection

1. Select the One Model app in ChatGPT
2. Enter a query that requires One Model data, such as:
   • What is my external hire rate trend?
   • What is my current headcount?

The query is routed through One Model’s MCP layer and returns a governed, data-driven response.

Tip: If you receive an error or no data, verify permissions, MCP URLs, and connector visibility.

Part 2: Business Users and Analysts

Connecting to and Using the One Model App 

Required Permissions

To connect ChatGPT to One Model, your user account must have an Application Access Role (AAR) with:

• CanAccessOneModelMCP enabled

This is managed by your One Model Administrator via: Admin > Application Access Role > [Select Role] > Permissions

Step 1: Log in to One Model

Log in (or use SSO) to your company’s One Model production instance.

Step 2: Connect the One Model App in ChatGPT

1. In ChatGPT, select Apps from the left panel 
2. Search for One Model 
3. Select the app and click Connect 
4. In the Connect One Model modal, click Continue to One Model

5. Review the consent page and click Accept

6. Click Start Chat

Once connected, the One Model app appears below the Ask anything prompt.

Note: After initial setup, the app can also be accessed via the + button in the chat interface.

Step 3: Test the App

Enter a query that requires One Model data, for example:

• What is my external hire rate trend?
• What is my current headcount?

ChatGPT will route the request through One Model’s MCP layer and return results based on governed workforce data.

Tip: If you encounter errors or no data, confirm that the app is visible, connected, and that you have the required permissions.

Feedback Form

We encourage beta testers to complete the Feedback Form to share what’s working well, report issues, and suggest enhancements.

If you experienced app visibility or discoverability issues, please note:

• Whether the app was newly published or republished
• Whether Developer Mode was enabled at the time