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 individual application pages.

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 relevant application page for what to collect)

Create an MCP server

Find the API in the catalog

1. Sign in to AI Gateway and select MCP Servers from the left navigation.
2. Select New MCP Server.
3. Search for the application you want to connect, then select it from the catalog.

Configure the server

1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
2. Enter a Description so your team knows what the server is for.
3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
4. Toggle Production mode on if this server will be used in a live workflow.
5. Select Next.

Configure authentication

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security

1. Set any Rate limits appropriate for your use case and the API's own limits.
2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
3. Select Next.

Deploy

Review the summary, then select 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:

• Claude Desktop
• Claude Code
• Cursor
• VS Code
• Windsurf

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.
• You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication

Adobe Analytics uses OAuth 2.0 via the Adobe Developer Console with the IMS (Identity Management System) service. The authorization endpoint is https://ims-na1.adobelogin.com/ims/authorize/v2, and the token endpoint is https://ims-na1.adobelogin.com/ims/token/v3. Create an OAuth credential in Developer Console, select your organization and product profile, and receive a Client ID and Client Secret. Scopes or product profiles determine which Analytics features and report suites your integration can access—select profiles that match your reporting needs (e.g., Analytics Analyst for standard reporting, Admin for configuration changes).

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).