About Release 8.2.0
This site contains documentation for HPE Data Fabric release 8.2.0, including installation, configuration, administration, and reference content, as well as content for the associated ecosystem components and drivers.
8.2.0 Installation
This section contains information about installing HPE Data Fabric software. It also contains information about how to migrate data and applications from an Apache Hadoop cluster to a HPE Ezmeral Data Fabric cluster.
8.2.0 Upgrade
This section describes how to upgrade HPE Data Fabric software.
8.2.0 Data Fabric
HPE Data Fabric is the industry-leading data platform for AI and analytics that solves enterprise business needs.
8.2.0 Administration
This section describes how to manage the nodes and services that make up a cluster.
8.2.0 Development
This section contains information related to application development for Ezmeral ecosystem components and HPE Data Fabric products, including the file system, Database (Key-Value and JSON), and Event Streams.
- Application Development Process
  Before you start developing applications on the HPE Data Fabric platform, consider how you will get the data into the platform, the storage format of the data, the type of processing or modeling that is required, and how the data will be accessed.
- File Store and Apps
  The following sections provide information about accessing the File Store with C and Java applications.
- HPE Data Fabric Database and Apps
  This section contains information about developing client applications for JSON and key-value tables.
- Apache Kafka Wire Protocol Service
  HPE Data Fabric Streams supports Apache Kafka Wire Protocol Service. Apache Kafka Wire Protocol Service is a TCP/IP service that emulates a Kafka cluster backed by HPE Data Fabric Streams. The service makes it possible for Apache Kafka clients written in any programming language to access topics in HPE Data Fabric Streams.
- Model Context Protocol (MCP)
  - Getting Started with Data Fabric MCP
  - Configuring Data Fabric MCP Server
    This topic describes the configuration file and settngs for the Data Fabric MCP server. The configuration file /opt/mapr/data-access-gateway/conf/mcp-server.conf contains server options including network ports, SSL protocols, OAuth/SSO settings, and endpoint service configurations for Apache Spark and Apache Iceberg.
  - Data Fabric MCP Endpoints
  - Registering MCP Server with AI Applications
    This topics describes various configuration settings required for MCP.
  - Airflow MCP Integration for Agentic AI
    Airflow MCP lets AI clients that support the Model Context Protocol (MCP) view, run, troubleshoot and create Apache Airflow DAGs on your Data Fabric cluster, using your own identity.
    - Airflow MCP Prerequsities
      Check that your cluster, user accounts and client machine meet these requirements before you turn on Airflow MCP and connect an AI client.
    - Airflow MCP configuration properties
      Use these properties to turn on Airflow MCP and to control how it connects to Airflow, how it authenticates, how it checks user identity, and how it handles DAG uploads.
    - Airflow MCP security and authentication
      Airflow MCP authenticates both the AI client and the calls it makes to Airflow. It runs every action as the user who asked for it, blocks user impersonation, requires a person to approve AI-written DAGs, and encrypts traffic with the cluster's TLS certificates.
    - Connecting AI Clients to Airflow MCP
      Register the Airflow MCP endpoint in an AI client, such as Claude Desktop, Cursor or MCP Inspector, so the client can use Airflow MCP tools with your Data Fabric identity.
    - Airflow MCP tools reference
      Airflow MCP has 33 tools that AI clients can call to view, run, troubleshoot and create Airflow DAGs. This topic lists each tool, what it does, and whether it can change or delete data.
    - Creating DAGs with an AI Agent
      Ask an AI client to write an Airflow DAG, check the code it produces, and publish the DAG to Airflow. Airflow MCP uses two steps, review and then upload, so AI-written code can't reach Airflow until you approve it.
- HPE Data Fabric Streams and Apps
  HPE Data Fabric Streams brings integrated publish and subscribe messaging to HPE Data Fabric.
- MapReduce and Apps
  This section contains information associated with developing YARN applications.
- Kubernetes Interfaces for Data Fabric
  This section describes how to leverage the capabilities of the Kubernetes Interfaces for Data Fabric.
- Ecosystem Components
  The following sections provide information about each open-source project that is supported by the HPE Data Fabric.
- Maven and the HPE Data Fabric
  This section discusses topics associated with Maven and the HPE Data Fabric.
- Developer's Reference
  This section contains in-depth information for the developer.
- API Documentation
  HPE Data Fabric supports public APIs for file system, HPE Data Fabric Database, and HPE Data Fabric Streams. These APIs are available for application-development purposes.
Other Docs
This section contains release-independent information, including: Installer documentation, Ecosystem release notes, interoperability matrices, security vulnerabilities, and links to other Data Fabric version documentation.
Glossary
Definitions for commonly used terms in MapR Converged Data Platform environments.

Airflow MCP Integration for Agentic AI

Airflow MCP lets AI clients that support the Model Context Protocol (MCP) view, run, troubleshoot and create Apache Airflow DAGs on your Data Fabric cluster, using your own identity.

As of Data Fabric 8.2.0 and DEP 10.2.0, Airflow MCP is supported. Airflow MCP is an endpoint on the Data Fabric MCP server. The MCP server run inside the Data Access Gateway. It gives AI clients such as Claude Desktop, Cursor, and MCP Inspector a set of tools that call the Airflow REST API for you.

An Apache Airflow DAG (Directed Acyclic Graph) is a worflow definition that describes tasks and the order in which they should run. This not to be confused with Data Access Gateway, which controls how applications securely access data. In this section, DAG refers to an Airflow DAG unless otherwise noted.

With Airflow MCP, you can ask an Ai assistant to:

List your DAGs and check their status, schedule and run history
Start a DAG run and watch it until it finishes
Find out why a run failed, using its task states and logs
Pause or unpause DAGs, and clear failed runs or tasks so they can run again
Look up Airflow settings such as connections, variables, pools and providers
Follow data lineage through Airflow assets and asset events
Write a new DAG and publish it to Airflow after you review it

How Airflow MCP works

The AI client connects to the Data Fabric MCP server's Airflow endpoint at https://<host>:5679/airflow.
The MCP server checks who you are and passes your JWT identity to Airflow as a Bearer token.
The MCP server calls the Airflow REST API to run the tool the client asked for.
Airflow sends back the result, and the MCP server passes it to the AI client.

By default, the MCP server finds the Airflow service on the cluster by itself. Administrators can also set the Airflow REST URL themselves.

Partners Support Dev-Hub Community ALA Privacy Policy Glossary

HPE Data Fabric 8.2.0 Software Documentation
Abstract	This site contains documentation for HPE Data Fabric Software version 8.2.0 including installation, configuration, administration, and reference content, as well as content for the associated bundled ecosystem components and drivers.
Published	October 2026
Edition	8.2.0
Topic last updated	2026-09-29