Adobe Analytics MCP server
An AI agent connected to Adobe Analytics can generate custom reports, analyze visitor behavior, create audience segments, and measure campaign effectiveness—enabling marketing teams and data analysts to extract insights without accessing the Analytics UI. Marketing managers, product analysts, and data teams use this integration to automate reporting and feed analytics into broader business intelligence workflows.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers.
- API credentials for the application you're connecting (see the Authentication section on this page for what to collect).
Create an MCP server
Find the app in the catalog
- Sign in to AI Gateway and select App Catalog from the left navigation.
- Search for the application you want to connect, then select it from the catalog.
- Select Create MCP Server to start the wizard.
App Configuration
Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.
MCP Server Setup
- Enter a Name for your server — something descriptive that identifies both the application and its purpose.
- Enter a Description so your team knows what the server is for.
- Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
- Select Next.
Authentication
Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.
Review
Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
Authentication
Adobe Analytics uses OAuth 2.0 through the Adobe Developer Console with the IMS (Identity Management System) service. Create an OAuth credential in Developer Console, select your organization and product profile, and receive a Client ID and Client Secret. In Adobe Developer Console, go to console.adobe.io, create a new project, and add the Adobe Analytics API to generate your OAuth credentials.
| Value | Setting |
|---|---|
| Auth endpoint | https://ims-na1.adobelogin.com/ims/authorize/v2 |
| Token endpoint | https://ims-na1.adobelogin.com/ims/token/v3 |
Available tools
The MCP server provides report generation, segmentation, calculated metrics, real-time monitoring, and data export capabilities for comprehensive analytics access.
Reporting
| Tool | Description |
|---|---|
| getReport | Execute any Analytics report with custom metrics and dimensions |
| listAvailableReports | Discover reports available in your instance |
| generateCustomReport | Build ad-hoc report with specific metric, dimension, and date range |
| getReportData | Fetch report data in JSON format for programmatic use |
Segments & audiences
| Tool | Description |
|---|---|
| createSegment | Build audience segment with behavior or demographic criteria |
| listSegments | Retrieve all segments available in report suite |
| deleteSegment | Remove unused segment |
| getSegmentSize | Check segment member count before targeting |
Metrics & dimensions
| Tool | Description |
|---|---|
| listAvailableMetrics | Get all standard and calculated metrics |
| listAvailableDimensions | Retrieve available dimensions for reports |
| createCalculatedMetric | Build custom metric from existing metrics (e.g., revenue per visitor) |
| updateCalculatedMetric | Modify metric definition |
| getMetricDefinition | Retrieve metric formula and description |
Trends & anomalies
| Tool | Description |
|---|---|
| getTrendData | Retrieve metric values over time for trend analysis |
| getYoYComparison | Compare metric performance year-over-year |
| detectAnomalies | Identify unusual patterns or spikes in metrics |
| alertOnThreshold | Trigger notification when metric exceeds threshold |
Data export
| Tool | Description |
|---|---|
| exportReportToCSV | Download report as CSV file |
| scheduleDataWarehouseExport | Request large data export for offline analysis |
| exportToDataLake | Stream continuous analytics data to data warehouse |
| getDataFeed | Access raw hit-level data feed |
Tips
Use the Reports API for standardized reports already configured in your instance — custom reports are faster when they match existing templates.
Create calculated metrics once in Analytics and reuse them across reports and integrations rather than computing the same formula repeatedly via API.
Batch report requests and stagger them over time to avoid hitting concurrent request limits — schedule heavy analytics queries during off-peak hours.
Store segments and calculated metrics in Analytics so they're reusable across the platform and updated centrally — don't recreate them via API for each integration.
Monitor data freshness — Analytics processes data with some latency, so real-time dashboards may not reflect the very latest activity (typically 1–2 hour delay).
Cequence AI Gateway