Apache Airflow

v1.0.0Databasesstable

Provides a standardized way for MCP clients to interact with Apache Airflow's REST API, supporting operations like DAG management and monitoring Airflow system health.

mcp-server-for-apache-airflowmcpai-integration
Share:
165
Stars
0
Downloads
0
Weekly
0/5

What is Apache Airflow?

Apache Airflow is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides a standardized way for mcp clients to interact with apache airflow's rest api, supporting operations like dag management and monitoring airflow system health.

Provides a standardized way for MCP clients to interact with Apache Airflow's REST API, supporting operations like DAG management and monitoring Airflow system health.

This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Provides a standardized way for MCP clients to interact with

Use Cases

Manage DAGs and monitor Airflow workflows.
Interact with Apache Airflow's REST API through MCP.
Control and query data pipelines.
yangkyeongmo

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-server-for-apache-airflow

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Apache Airflow

The MCP Server for Apache Airflow provides AI clients with a standardized interface to Apache Airflow's REST API, covering DAG management, DAG run creation and monitoring, task instance inspection, variable and connection CRUD, pool management, XCom access, dataset event tracking, and system health monitoring. Platform engineers and data teams use it to query and control Airflow pipelines conversationally — triggering DAG runs, checking task logs, and monitoring pipeline health without switching to the Airflow UI.

Prerequisites

  • Python 3.10 or higher installed
  • A running Apache Airflow instance accessible via REST API (Airflow 2.x or higher)
  • Airflow username and password, or a JWT token for authentication
  • uvx or pip for installing the package
  • An MCP client such as Claude Desktop
1

Install the MCP server package

Install mcp-server-apache-airflow via pip or run directly with uvx. The uvx approach requires no permanent installation.

pip install mcp-server-apache-airflow
# Or run directly without installing:
uvx mcp-server-apache-airflow
2

Configure Airflow connection details

Set the environment variables for your Airflow host. AIRFLOW_HOST defaults to http://localhost:8080 and AIRFLOW_API_VERSION defaults to v1.

export AIRFLOW_HOST=http://your-airflow-host:8080
export AIRFLOW_API_VERSION=v1
# Basic auth:
export AIRFLOW_USERNAME=admin
export AIRFLOW_PASSWORD=your_password
# OR JWT auth:
export AIRFLOW_JWT_TOKEN=your_jwt_token
3

Add the server to Claude Desktop config

Register the server in claude_desktop_config.json. Use uvx for a zero-install approach or python -m if you installed via pip.

{
  "mcpServers": {
    "apache-airflow": {
      "command": "uvx",
      "args": ["mcp-server-apache-airflow"],
      "env": {
        "AIRFLOW_HOST": "http://your-airflow-host:8080",
        "AIRFLOW_USERNAME": "admin",
        "AIRFLOW_PASSWORD": "your_password"
      }
    }
  }
}
4

Enable read-only mode for safe exploration

Set READ_ONLY to 'true' to restrict the server to GET operations only, preventing any modifications to your Airflow environment during initial exploration.

export READ_ONLY=true
5

Restart Claude Desktop and verify

Restart Claude Desktop to load the server. Ask Claude to list your DAGs to confirm the connection is working.

Apache Airflow Examples

Client configuration

Claude Desktop configuration for the Apache Airflow MCP server using uvx with basic authentication.

{
  "mcpServers": {
    "apache-airflow": {
      "command": "uvx",
      "args": ["mcp-server-apache-airflow"],
      "env": {
        "AIRFLOW_HOST": "http://localhost:8080",
        "AIRFLOW_API_VERSION": "v1",
        "AIRFLOW_USERNAME": "admin",
        "AIRFLOW_PASSWORD": "admin",
        "READ_ONLY": "false"
      }
    }
  }
}

Prompts to try

Example prompts to use once the Airflow MCP server is connected to Claude Desktop.

- "List all active DAGs in my Airflow instance"
- "Trigger a run for the DAG named 'daily_etl_pipeline'"
- "Show me the last 5 runs for DAG 'data_ingestion' and their statuses"
- "Get the task log for task 'transform_data' in the most recent run of DAG 'etl_workflow'"
- "List all Airflow variables and their values"
- "Check the health status of my Airflow instance"
- "What connections are configured in Airflow?"

Troubleshooting Apache Airflow

Authentication fails with 401 Unauthorized when connecting to Airflow

Verify AIRFLOW_USERNAME and AIRFLOW_PASSWORD match a valid Airflow user. For JWT authentication, ensure AIRFLOW_JWT_TOKEN is current (tokens typically expire). Do not set both basic and JWT credentials simultaneously — choose one method.

Connection refused when the server tries to reach Airflow

Confirm AIRFLOW_HOST is reachable from where the MCP server runs. If Airflow is on a remote host, ensure network access and firewall rules allow the connection. Test with 'curl http://your-airflow-host:8080/health'. For Docker-based Airflow, you may need to use the container's network IP rather than localhost.

uvx command not found

Install uv first: 'curl -LsSf https://astral.sh/uv/install.sh | sh'. After installation, reload your shell or add uv's bin directory to your PATH. Alternatively use 'pip install mcp-server-apache-airflow' and run with 'python -m mcp_server_apache_airflow' instead.

Frequently Asked Questions about Apache Airflow

What is Apache Airflow?

Apache Airflow is a Model Context Protocol (MCP) server that provides a standardized way for mcp clients to interact with apache airflow's rest api, supporting operations like dag management and monitoring airflow system health. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Apache Airflow?

Follow the installation instructions on the Apache Airflow GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Apache Airflow?

Apache Airflow works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Apache Airflow free to use?

Yes, Apache Airflow is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-server-for-apache-airflow": { "command": "npx", "args": ["-y", "mcp-server-for-apache-airflow"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Apache Airflow?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides