Adobe Experience Platform MCP server

An AI agent connected to Adobe Experience Platform can unify customer data, build audience segments, activate campaigns across channels, and orchestrate personalized journeys—enabling marketing and data teams to leverage the customer data platform without manual console access. Marketing managers, data engineers, and customer insights teams use this integration to automate data ingestion, audience management, and campaign activation at scale.

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 Experience Platform uses OAuth 2.0 via the Adobe Developer Console with server-to-server OAuth 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 server-to-server credential in Developer Console, select product profiles that grant access to Platform services (e.g., AEP Platform Admin, Data Manager), and receive Client ID and Client Secret. Scopes are automatically assigned based on product profiles—align profile selection to the operations your integration performs.

Available tools

The MCP server provides customer profile management, segmentation and audience activation, data ingestion and governance, and journey orchestration capabilities for comprehensive CDP operations.

Customer profiles

Tool	Description
getCustomerProfile	Retrieve unified profile for specific customer with all touchpoints
updateCustomerProfile	Modify profile attributes and preferences
mergeProfiles	Combine duplicate profiles for same person
getProfileAttributes	Retrieve all profile fields and custom attributes
getProfileExperiences	Get customer journey and interaction history

Segmentation & activation

Tool	Description
createSegment	Build audience with behavioral, demographic, or predictive criteria
updateSegment	Modify segment rules and member criteria
activateSegment	Publish segment to marketing channels and destinations
getSegmentMembers	Retrieve list of segment members with attributes
estimateSegmentSize	Get segment member count before activation
getSegmentMetrics	Track segment growth and member churn over time

Data ingestion & management

Tool	Description
ingestBatchData	Upload batch of customer records to Platform
streamData	Ingest real-time events from website or app
createDataset	Create new dataset for specific data source
validateSchema	Check incoming data against XDM schema
applyDataGovernanceLabel	Tag data fields with usage policies
enforceDataAccessPolicy	Control who can access sensitive data

Journey orchestration

Tool	Description
createJourney	Design multi-step orchestrated experience
activateJourney	Launch journey for real-time contacts
getJourneyMetrics	Retrieve conversion, engagement, and drop-off rates
updateJourneyOffer	Change offer or message based on performance
testJourneyVariant	A/B test different journey paths

Analytics & insights

Tool	Description
queryData	Execute SQL query on Platform data lake
getAttributionMetrics	Retrieve multi-touch attribution for conversions
getPredictiveScore	Get machine learning score (churn, lifetime value)
exportAnalytics	Download analytical results for external tools

Tips

Use server-to-server OAuth credentials exclusively for backend automation — never expose Client Secret in client-side code or logs.

Design schemas and datasets once and reuse them across all data sources to maintain consistency and simplify governance.

Batch customer data imports using the Batch Ingestion API rather than individual record writes — bulk operations are more efficient and reduce API call overhead.

Apply data governance labels at ingestion to enforce privacy policies automatically and prevent unauthorized access to sensitive fields.

Test journey variants on a small segment before activation to validate messaging and success metrics.