MCP Adobe Experience Platform Server
LocalAbout MCP Adobe Experience Platform Server
A Node.js MCP server that provides an API interface to Adobe Experience Platform for teams managing AEP data and configuration. It covers schemas, datasets, segments, profiles, and queries.
Key features
- 01Manage schemas and datasets
- 02Manage segments and profiles
- 03Ingest data into datasets
- 04Run Query Service queries
- 05Manage destinations and activate segments
- 06Swagger docs and input validation
Use cases
- 01Create or inspect AEP schemas and datasets
- 02Ingest data into a selected dataset
- 03Retrieve a unified profile
- 04Run queries and activate a destination segment
MCP support
The project is an MCP server that exposes Adobe Experience Platform API operations to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Adobe Experience Platform Server
This is a Node.js server that provides a comprehensive API interface for Adobe Experience Platform (AEP) integration. It supports various AEP functionalities including schemas, datasets, segments, profiles, and more.
Features
- Schema Management
- Dataset Operations
- Segment Management
- Data Ingestion
- Profile Management
- Query Service
- Destinations Management
- Swagger Documentation
- Input Validation
- Error Handling
Prerequisites
- Node.js (v14 or higher)
- npm or yarn
- Adobe Experience Platform account with API access
- Adobe Developer Console project with AEP integration
Setup
- Clone the repository:
git clone https://github.com/praveensharmajava/mcp-adobe-aep.git
cd mcp-adobe-aep
- Install dependencies:
npm install
- Create a
.envfile in the root directory with your Adobe credentials:
PORT=3000
AEP_BASE_URL=https://platform.adobe.io
AEP_CLIENT_ID=your_client_id
AEP_CLIENT_SECRET=your_client_secret
AEP_ORG_ID=your_organization_id
- Build the project:
npm run build
- Start the server:
npm start
For development:
npm run dev
API Documentation
Once the server is running, you can access the Swagger documentation at:
http://localhost:3000/api-docs
API Endpoints
Schemas
- GET /api/aep/schemas - List all schemas
- POST /api/aep/schemas - Create a new schema
Datasets
- GET /api/aep/datasets - List all datasets
- POST /api/aep/datasets - Create a new dataset
Segments
- GET /api/aep/segments - List all segments
- POST /api/aep/segments - Create a new segment
Data Ingestion
- POST /api/aep/ingest/:datasetId - Ingest data into a dataset
Profiles
- GET /api/aep/profiles/:identityValue - Get unified profile
Query Service
- POST /api/aep/query - Execute a query
Destinations
- GET /api/aep/destinations - List all destinations
- POST /api/aep/destinations/:destinationId/activate/:segmentId - Activate a segment
Error Handling
The server includes comprehensive error handling for:
- Adobe API errors
- Connection issues
- Validation errors
- Internal server errors
Development
To contribute to the project:
- Create a new branch
- Make your changes
- Write/update tests
- Submit a pull request
Testing
Run the test suite:
npm test
License
ISC
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.