MCP Public
Anmelden
A

Airflow

Trigger and inspect Apache Airflow DAGs.

·No reviews yet
Repo
Share:

About

Auto-generated

Airflow is a Model Context Protocol server in the Data & Databases category. It lets AI assistants that speak MCP call its tools and read its resources over STDIO.

Example tools

Illustrative tool names — the actual tool set is defined by the server at runtime.

query
Run a read-only SQL query
list_tables
List tables in the connected database
describe_table
Return column info for a table

Screenshots

No screenshots yet.

Frequently Asked Questions

Common questions about Airflow.

What is the Airflow MCP and what does it do?
The Airflow MCP allows you to trigger and inspect Apache Airflow Directed Acyclic Graphs (DAGs). This enables external systems to manage and monitor Airflow workflows programmatically.
How do I install the Airflow MCP in an MCP client like Cline?
Installation in Cline typically involves adding the MCP's repository URL to Cline's configuration. The Airflow MCP's repository is located at https://github.com/yangkyeongmo/mcp-server-apache-airflow. Follow Cline's documentation for specific installation steps.
Does the Airflow MCP require an API key or other credentials?
Yes, the Airflow MCP uses an API key for authentication. You will need to configure your API key within your MCP client to access and interact with your Airflow instance securely.
What are the primary capabilities of the Airflow MCP?
The Airflow MCP primarily provides functionality for triggering and inspecting Apache Airflow DAGs. This includes initiating DAG runs, checking their status, and reviewing execution logs, enabling external workflow orchestration.
What are the costs associated with using the Airflow MCP?
The Airflow MCP itself is open-source and provided by the community, so there are no direct costs for the MCP software. However, running Apache Airflow instances may incur costs based on your deployment infrastructure and cloud provider, if applicable.
Are there any prerequisites for using the Airflow MCP?
A prerequisite for using the Airflow MCP is a running and accessible Apache Airflow instance. You must also have appropriate permissions and an API key configured for your Airflow environment to allow external access.

Install Airflow

Claude Desktop

Add this to claude_desktop_config.json.

{
  "mcpServers": {
    "airflow": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-airflow"
      ]
    }
  }
}

Cursor

Add this to ~/.cursor/mcp.json.

{
  "mcpServers": {
    "airflow": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-airflow"
      ]
    }
  }
}

VS Code

Add this to your workspace settings.json.

{
  "mcp.servers": {
    "airflow": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-airflow"
      ]
    }
  }
}

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Discussion(0)

Sign in to join the discussion.

No comments yet.