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

Please Note: One Model's MCP integration is currently in an early-access phase. Because AI platforms update their interfaces frequently, you may find that some buttons, menu names, or configuration steps have shifted slightly since this guide was published. System Variations: Steps may vary depending on your specific tenant setup, regional settings, or administrative permissions. Help Us Improve: If a step looks different in your system or you encounter an unexpected result, please let us know! Use the Feedback Form to help us refine these instructions for the final release.

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 to both platforms.

Required Permissions in One Model

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
• CanRegisterMCPClients - Controls whether the user can manage pre-registration credentials for MCP clients
• CanConfigureCompany - Grants access to high-level company settings

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

Choose your Client Registration Path

There are two ways to register ChatGPT as an MCP client in One Model. Both result in a working connection - the difference is who controls the client credentials and how the connection is approved.

Path 1 - Register a Dedicated MCP Client (recommended)

• You generate dedicated OAuth credentials in One Model and paste them into ChatGPT. You stay in control of credentials and can revoke them independently.

Path 2 - Automatic Client Registration

• ChatGPT registers itself automatically using Dynamic Client Registration (DCR), governed by an approved Integration Rule you create in One Model. Because the credentials are generated dynamically rather than by you, this path offers less control than Path 1 - we recommend Path 1 wherever it's available to you.

Path 1 - Register a Dedicated MCP Client (recommended)

This path generates a dedicated OAuth Client ID and Client Secret that you paste into ChatGPT's app configuration. Use this approach when you want to control the credentials yourself rather than relying on dynamic registration.

Note on order of steps: ChatGPT generates its OAuth Callback URL inside the app creation screen, so you'll begin creating the app in ChatGPT first, register the client in One Model, and then return to ChatGPT to finish.

Step 1 - Begin creating the App in ChatGPT

1. Log into ChatGPT
2. Open Settings (via your profile icon)
3. Navigate to Security and login
4. Turn Developer Mode on then close this settings panel

5. Open Workspace Settings (via your profile icon)
6. Click Apps
7. Click the Create button
8. Configure the One Model connection:
   • App Name: e.g., One Model
   • MCP Server URL: the endpoint for your One Model MCP server
     • Be sure to use the correct URL for your Production environment
     • Your MCP Server URL is based on your One Model site URL - add api. before your company ID and /mcp at the end
     • One Model URLs use one of these domains: onemodel.us, onemodel.com.au, onemodel.ca, or onemodel.eu
     • Example: https://api.[companyid].onemodel.[us]/mcp
   • Authentication Method: OAuth
   • Open the Advanced OAuth Settings and set the Registration Method to User-Defined OAuth Client
   • Locate the Callback URL field and click the Copy icon

Keep this ChatGPT window open; you will return here.

Step 2 - Register the client in One Model

1. Log into your One Model production instance
2. Navigate to Admin > Integration
3. Open the MCP Clients tab and click Register New Client

4. Complete the registration form:
   • Client Name: A descriptive label that identifies this client in audit logs and the MCP Clients list, e.g. ChatGPT Production
   • Redirect URL: Paste the Callback URL you copied from ChatGPT in Step 1
5. Click Register

Capture your credentials

Once the client is registered, One Model will display the OAuth Client ID and OAuth Client Secret.

Important: Copy both values to a secure location before navigating away from the page. If you lose the secret, you'll need to register a new client.

Step 3 - Finish the App in ChatGPT

1. Return to your ChatGPT 'New App' window (Registration Method should still be set to User-Defined OAuth Client)
2. Paste the OAuth Client ID and OAuth Client Secret you captured in Step 2 into the corresponding fields. The rest of the fields will be automatically filled in for you.
3. On the main panel, click the checkbox “I understand and want to continue”.
4. Click Create

Next step: You've completed Path 1. Skip Path 2 below and go straight to Accept Permissions.

Path 2 - Automatic (Dynamic) Client Registration

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.

Begin creating the App in ChatGPT

1. Log into ChatGPT
2. Open Settings (via your profile icon)
3. Navigate to Security and login
4. Turn Developer Mode on then close this settings panel

5. Open Workspace Settings (via your profile icon)
6. Click Apps
7. Click the Create button
8. Configure the One Model connection:
   • App Name: e.g., One Model
   • MCP Server URL: as described above (e.g. https://api.[companyid].onemodel.us/mcp)
   • Authentication Method: OAuth
   • Open  Advanced OAuth Settings and change the Registration Method to User-Defined OAuth Client
   • Locate the Callback URL field and click the Copy icon

Keep this ChatGPT window open; you will return here.

Create the Client Integration in One Model

1. Log into your One Model production instance
2. Navigate to Admin > Integration
3. Click Create New and select Custom 
   • If using Custom: in the Metadata Field, type redirect_uris, and in Allowed Values, paste the Callback URL you copied from ChatGPT
4. Click Save

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

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

Finalize the Publish in ChatGPT

1. Return to your ChatGPT 'Create App' window
2. Under Advanced Settings, change the Registration Method back to Dynamic Client Registration (DCR)
3. On the main panel, click the checkbox “I understand and want to continue”.
4. Click Create

Publishing the Connector

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

Publish the App

1. You should automatically see the new connector and an option to Publish. This might take a few seconds to show up.
2. If you don’t see it, search for 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

Next step: You've completed Path 2. Continue to Connect and Accept Permissions.

Connect and Accept Permissions

Locate the One Model connector you just published in the Plugins directory and click the name of the Connector tp open it.

Click the Connect button

Click the Continue to [your connector name]… button

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.

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.

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

Log in to One Model

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

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.

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