Adobe Target MCP server

An AI agent connected to Adobe Target can automate experimentation and personalization—creating and running A/B tests, building audience-based experiences, activating product recommendations, and measuring test performance. Digital marketers, optimization specialists, and product teams use this integration to streamline testing workflows and deploy personalized experiences across web and mobile without manual console access.

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 Target uses OAuth 2.0 via the Adobe Developer Console with server-to-server credentials. 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 product profiles that grant access to Target Admin APIs, and receive Client ID and Client Secret. Scopes are assigned based on product profiles—align profile selection with the operations your integration performs (activity creation, reporting, audience management, etc.).

Available tools

The MCP server provides activity management, audience operations, offer management, personalization, and analytics for complete experimentation and personalization.

A/B testing & activities

Tool	Description
createActivity	Create A/B test, multivariate test, or experience targeting activity
updateActivity	Modify traffic allocation, targeting rules, success metrics
activateActivity	Launch activity for real-time traffic
pauseActivity	Temporarily halt activity (maintains state)
getActivityMetrics	Retrieve conversion lift, statistical significance, winner
deleteActivity	Archive completed activity

Audiences & targeting

Tool	Description
createAudience	Build audience with behavioral, demographic, or custom attributes
updateAudience	Modify audience rules and member criteria
listAudiences	Get available audiences for targeting
getAudienceSize	Estimate audience member count
createAudienceCombination	Combine multiple audiences with AND/OR logic
getAudienceMembers	Retrieve audience member list

Offers & personalization

Tool	Description
createOffer	Create HTML, JSON, image, or redirect offer
updateOffer	Modify offer content and properties
deleteOffer	Remove unused offer
listOffers	Retrieve available offers by type
tagOffer	Add labels to offers for organization
createRecommendationOffer	Set up product recommendation algorithm

Personalization & AI

Tool	Description
createAutoTargetActivity	Enable machine learning optimization
createAutomatedPersonalizationActivity	Create AI-driven personalization activity
createAutoAllocateActivity	Enable traffic auto-allocation to winning variant
getMLModelMetrics	Retrieve model performance and insights
testJourneyVariant	A/B test different personalization paths

Analytics & reporting

Tool	Description
getActivityReport	Retrieve detailed activity performance metrics
getConversionLift	Calculate uplift percentage and confidence
getVisitorAnalytics	Track visitor segments and experience distribution
exportActivityData	Download activity results for external analysis
getAudienceInsights	Analyze audience overlap and characteristics

Tips

Start with simple A/B tests before advanced AI activities (Auto-Target, Automated Personalization) to validate test infrastructure and learn baseline performance.

Define success metrics clearly before activity launch and avoid changing them mid-test to maintain statistical validity.

Use audiences from Experience Platform or your CDP to enable sophisticated targeting based on unified customer data rather than behavioral signals alone.

Monitor statistical significance and confidence levels before declaring winners — stop tests when you reach 95% confidence to avoid wasted traffic.

Archive completed activities rather than deleting them to preserve historical data for trend analysis and future reference.