Apache Airflow
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.
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
Maintainer
Works with
Installation
Manual Installation
npx mcp-server-for-apache-airflowConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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-airflowConfigure 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_tokenAdd 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"
}
}
}
}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=trueRestart 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.
Apache Airflow Alternatives — Similar Databases Servers
Looking for alternatives to Apache Airflow? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
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.
Set Up Apache Airflow in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.