This article covers the following:
- Overview
- Wingify MCP Authentication
- Supported MCP Tools
- Connect Wingify MCP Server with ChatGPT
- FAQs
Overview
The Wingify Model Context Protocol (MCP) server is a secure connection layer that enables external AI tools, such as ChatGPT, n8n, or other automation systems, to connect with your Wingify account. It allows these tools to directly access and analyze your live Wingify campaign data and insights using simple natural-language queries. Think of it as a secure digital bridge that turns Wingify data into an AI-native app, eliminating the need to manually export reports and copy/paste data for external analysis or workflow automation.
Integrating third-party AI tools like ChatGPT with the Wingify MCP server offers the following benefits:
- Instant, on-demand insights: You get data-backed answers for any questions around your campaign in seconds. This prevents you from navigating through multiple screens or exporting CSVs.
- Effortless data analysis: Use natural language to ask complex questions about your experiments and user behavior.
- Automated workflows: Connect Wingify to automation platforms (such as n8n or Zapier) to create powerful, cross-platform workflows, including automated weekly reports sent directly to Slack.
- Deep integration: Allow your AI assistant to fetch and segment all the data available in your Wingify account.
Let us understand the use of the Wingify MCP server better with a few use cases:
- For the Product Marketer: Instantly identify campaigns that are not producing a clear winner. Ask, Tell me about the campaigns that do not have a winner in the last 3 months? to get a complete list and start optimizing.
- For the Conversion Rate Optimization (CRO) Experts: Get a comprehensive behavioral summary for a key page. Ask, Can you access my heatmap for wingify.com/pricing and give me insights? to receive key takeaways, frustration indicators, and even visual heatmap previews.
- For the Data Analysts: Quickly drill down into user session recordings for deeper context. Ask follow-up questions like, What about session recordings for the same timeframe and page? to get a summarized breakdown of user interactions, device splits, and top regions.
Before understanding how to connect the Wingify MCP server with third-party AI tools like ChatGPT or Claude, let us understand how Wingify MCP authentication works and the tools it supports.
Wingify MCP Authentication
Wingify MCP Authentication Wingify MCP now supports full OAuth 2.0 authentication with Dynamic Client Registration. This means you do not need to manually generate or manage API tokens for ChatGPT, Claude or other tools; the authentication flow is handled automatically.
Select the MCP server URL from the following table based on your account region.
| Region | MCP Server URL |
|---|---|
| Global | https://mcp.wingify.ai/mcp |
| Europe | https://mcp-eu.wingify.ai/mcp |
| Asia | https://mcp-as.wingify.ai/mcp |
When you add this URL to your AI tool:
- You are redirected to the Wingify authorization screen.
- Select the Wingify account you want to connect.
- Choose the permission level to grant to the AI tool.
You have completed authentication, and the connection is ready.
Supported MCP Tools
Once the MCP server is connected, the following tools are available to AI clients through the Wingify MCP server:
| Tool | Type | Description |
|---|---|---|
| Calculate Sample Size | Read | Calculate the required sample size for a Bayesian A/B test campaign. |
| Get Wingify Campaign Daily Data | Read | Retrieve daily performance metrics for a specific campaign. |
| Get Wingify Campaign Report | Read | Fetch a full report for any Wingify campaign, including variations and goals. |
| Get Wingify Account Details and Configuration | Read | Access account-level settings and configuration details. |
| Get Wingify Campaign Variation Code | Read | Retrieve the code associated with a specific campaign variation. |
| Get Wingify Campaigns List Overview | Read | List all campaigns in the account with summary data. |
| Get Wingify data360 entities | Read | Access Data360 entity data, including visitor segments and attributes. |
| Analyze Wingify Heatmap Data | Read | Analyze heatmap data for a page, including click and scroll patterns. |
| Analyze Wingify Recording Data | Read | Summarize session recording data for a given page or time period. |
| Clone Wingify Campaign | Write | Create a copy of an existing Wingify campaign. |
| Create Wingify A/B Test/Campaign | Write | Create a new A/B test campaign from a natural language description. |
| Create Wingify Split URL Test/Campaign | Write | Create a new Split URL test campaign. |
| Update Wingify Campaign Configuration | Write | Modify settings of an existing campaign. |
| Update Wingify Campaign Status | Write | Start, pause, or stop a campaign. |
Connect Wingify MCP Server with ChatGPT
Prerequisites
- You must have a Wingify Enterprise plan or the Developer Plus add-on enabled.
- You must have a ChatGPT Pro, Plus, Team, or Enterprise subscription.
Follow the steps below to integrate the Wingify MCP server with your ChatGPT account:
Step 1: Enable Developer Mode in ChatGPT
Note: Use the official ChatGPT website to follow the steps below. To add Wingify as a custom connector within ChatGPT:
- Log in to your ChatGPT account.
- Go to Settings > Apps > Advanced settings > Developer mode.
- Toggle on the Developer mode. This allows you to add and configure custom connectors.
Note: Developer Mode allows unverified connectors that could modify or erase data. Only proceed with MCP servers from developers you trust.
Step 2: Configure Custom Wingify Connector in ChatGPT
To add Wingify as a custom connector within ChatGPT:
- Log in to your ChatGPT account.
- Go to Settings > Apps.
- Click Create app to add a new custom connector.
- Enter the following configuration details for the Wingify connector:
- Name: Enter a name that helps you recognize the connector (Wingify in this case).
- Description: Provide a short description that describes the capabilities of the connector
- MCP server URL: Set the MCP server URL as https://mcp.wingify.ai/mcp
- Authentication: Set Authentication to OAuth.
- Select the I understand and want to continue checkbox.
- Click Create.
Step 3: Authorize Wingify Access
After you click Create, follow these steps on the Wingify authorization screen:
- From the Select an account dropdown, choose the Wingify account you want to connect.
- From the Permission level dropdown, choose the permissions to grant to ChatGPT.
- You can select from the following permissions to manage how end users interact with Wingify data through the MCP server.
Permission Description Browse Read-only access to Wingify data, session recordings, heatmaps, A/B tests, Split URL, and Multivariate tests. Cannot create or edit. Design Enables creation of new A/B or Split URL tests via the MCP. Publish / Admin Provides full control to create, edit, start, pause, or delete A/B tests and Split URL tests. - Select the acknowledgment check box.
- Click Approve.
Step 4: Verify the Connection
Once you complete authorization, follow these steps to verify if your Wingify app connection is successful:
- Go to ChatGPT Settings > Apps
- Select the Wingify app and verify the following details:
- Connected on: the current date
- URL: https://mcp.wingify.ai/mcp
- Authorization supported / used: OAuth
- Scroll down to the Actions section to verify that the full list of available Wingify tools appears.
Step 5: Query Your Wingify Data Using Natural Language
Once the Wingify connector is configured, activate it before asking campaign-related queries. To activate the connector:
- On your ChatGPT account dashboard, navigate to the Ask anything field and click +.
- Select Wingify from the connectors list to activate it.
- Alternatively, type @Wingify before your question to direct it to Wingify.
-
Start asking your questions in natural language. To answer your questions, ChatGPT calls the Wingify MCP server to fetch the relevant data. If the query is successful, the system displays a Calling tool message in the ChatGPT interface before the results appear. This indicates that the connector is working successfully.
For best results, make your questions as specific as possible. Include campaign names, page URLs, and date ranges (for example, share the progress of campaigns that were published in the last 7 days).
FAQs
-
What is the difference between the Wingify MCP Server and Wingify AI?
The Wingify MCP server is a headless backend system that enables external tools, such as ChatGPT, to connect to your Wingify data. Wingify AI is a self-contained, in-app assistant that helps you with tasks inside the Wingify platform. -
Can I use the Wingify MCP Server to create a new campaign and manage its lifecycle?
Yes, currently, the Wingify MCP server allows third-party AI tools to create and manage only A/B tests and Split URL campaigns. -
Can I connect Wingify MCP with Microsoft Copilot?
The standard version of Microsoft Copilot does not currently support MCP connections. However, Microsoft Copilot Studio users can connect to Wingify MCP. For more information, see Introducing MCP in Copilot Studio.
Need more help?
For further assistance or more information, contact Wingify Support.