io.github.abhishekbhakat/airflow-mcp-server MCP Server
io.github.abhishekbhakat/airflow-mcp-server
Control Apache Airflow via Claude and Cursor with read/write access to DAGs, tasks, connections, and more.
What is the io.github.abhishekbhakat/airflow-mcp-server MCP server?
The Airflow MCP server is a Model Context Protocol server that enables AI agents like Claude to control and manage Apache Airflow instances through the Airflow REST API. It supports both read-only (safe mode) and full read-write operations, with configurable tool discovery and multiple transport protocols.
This server bridges Claude and Cursor to your Airflow deployment, allowing you to trigger DAG runs, monitor task execution, manage connections, and perform administrative operations programmatically. It's useful for automating Airflow management tasks, debugging workflows, and integrating Airflow operations into AI-assisted development workflows.
How to install io.github.abhishekbhakat/airflow-mcp-server
Copy-paste configuration for popular MCP clients.
AIRFLOW_BASE_URLrequiredThe base URL for the Airflow API (e.g., http://localhost:8080)
AUTH_TOKENrequiredsecretThe JWT authentication token for Airflow API access
Tools & capabilities
Tools this server exposes to the agent.
DAG Management— List, trigger, and manage DAGs in your Airflow instanceTask Operations— Monitor, retry, and manage individual task executionsConnection Management— Create, update, and manage Airflow connectionsVariable Management— Manage Airflow variables and configurationPool Management— Manage resource pools for task executionXCom Operations— Access and manage cross-communication data between tasksLog Retrieval— Fetch task and DAG execution logsHealth Monitoring— Check Airflow instance health and status
Use cases
- Trigger and monitor DAG runs from Claude without leaving your chat interface
- Retrieve task logs and execution history for debugging workflow issues
- Manage Airflow connections and variables programmatically through natural language
- Automate routine Airflow administrative tasks like pool and variable updates
- Monitor Airflow health and get real-time status updates on running tasks
io.github.abhishekbhakat/airflow-mcp-server MCP server FAQ
It's an MCP server that connects Claude or Cursor to your Apache Airflow instance, allowing you to control DAGs, tasks, connections, and other Airflow resources via the Airflow REST API.
Yes, it's open-source and available on PyPI as 'airflow-mcp-server'.
Add it to your Claude Desktop config.json under mcpServers with the command 'uvx airflow-mcp-server' and pass your Airflow base URL and JWT authentication token as arguments.
Only JWT token authentication is supported for Airflow 3.0. You must provide a valid JWT token via the --auth-token parameter.
Yes, use the --safe flag to enable read-only mode, which restricts the server to GET requests only.
The server supports stdio (default), HTTP/Streamable HTTP, and deprecated SSE transport. HTTP is recommended for web deployments and scalability.
README (reference)
Source of truth, from the repository.
airflow-mcp-server: An MCP Server for controlling Airflow 3
mcp-name: io.github.abhishekbhakat/airflow-mcp-server
MCPHub Certification
This MCP server is certified by MCPHub. This certification ensures that airflow-mcp-server follows best practices for Model Context Protocol implementation.
Find on Glama
<a href="https://glama.ai/mcp/servers/6gjq9w80xr"> <img width="380" height="200" src="https://glama.ai/mcp/servers/6gjq9w80xr/badge" /> </a>Overview
A Model Context Protocol server for controlling Airflow via Airflow APIs.
Demo Video
https://github.com/user-attachments/assets/f3e60fff-8680-4dd9-b08e-fa7db655a705
Setup
Usage with Claude Desktop
Stdio Transport (Default)
{
"mcpServers": {
"airflow-mcp-server": {
"command": "uvx",
"args": [
"airflow-mcp-server",
"--base-url",
"http://localhost:8080",
"--auth-token",
"<jwt_token>"
]
}
}
}
See CONFIG.md for IDE-specific configuration examples across popular MCP clients.
HTTP Transport
{
"mcpServers": {
"airflow-mcp-server-http": {
"command": "uvx",
"args": [
"airflow-mcp-server",
"--http",
"--port",
"3000",
"--base-url",
"http://localhost:8080",
"--auth-token",
"<jwt_token>"
]
}
}
}
Note:
- Set
base_urlto the root Airflow URL (e.g.,http://localhost:8080).- Do not include
/api/v2in the base URL. The server will automatically fetch the OpenAPI spec from${base_url}/openapi.json.- Only JWT token is required for authentication. Cookie and basic auth are no longer supported in Airflow 3.0.
Transport Options
The server supports multiple transport protocols:
Stdio Transport (Default)
Standard input/output transport for direct process communication:
airflow-mcp-server --safe --base-url http://localhost:8080 --auth-token <jwt>
HTTP Transport
Uses Streamable HTTP for better scalability and web compatibility:
airflow-mcp-server --safe --http --port 3000 --base-url http://localhost:8080 --auth-token <jwt>
Note: SSE transport is deprecated. Use
--httpfor new deployments as it provides better bidirectional communication and is the recommended approach by FastMCP.
Operation Modes
The server supports two operation modes:
- Safe Mode (
--safe): Only allows read-only operations (GET requests). This is useful when you want to prevent any modifications to your Airflow instance. - Unsafe Mode (
--unsafe): Allows all operations including modifications. This is the default mode.
To start in safe mode:
airflow-mcp-server --safe
To explicitly start in unsafe mode (though this is default):
airflow-mcp-server --unsafe
Tool Discovery Modes
The server supports two tool discovery approaches:
- Hierarchical Discovery (default): Tools are organized by categories (DAGs, Tasks, Connections, etc.). Browse categories first, then select specific tools. More manageable for large APIs.
- Static Tools (
--static-tools): All tools available immediately. Better for programmatic access but can be overwhelming.
To use static tools:
airflow-mcp-server --static-tools
Command Line Options
Usage: airflow-mcp-server [OPTIONS]
MCP server for Airflow
Options:
-v, --verbose Increase verbosity
-s, --safe Use only read-only tools
-u, --unsafe Use all tools (default)
--static-tools Use static tools instead of hierarchical discovery
--base-url TEXT Airflow API base URL
--auth-token TEXT Authentication token (JWT)
--http Use HTTP (Streamable HTTP) transport instead of stdio
--sse Use Server-Sent Events transport (deprecated, use --http
instead)
--port INTEGER Port to run HTTP/SSE server on (default: 3000)
--host TEXT Host to bind HTTP/SSE server to (default: localhost)
--help Show this message and exit.
Using Resources
Point the server at a folder of Markdown guides whenever you want agents to reference local documentation:
airflow-mcp-server --base-url http://localhost:8080 --auth-token <jwt> --resources-dir ~/airflow-resources
- Every top-level
.md/.markdownfile becomes a read-only resource (file:///<slug>) visible in your MCP client. - The first
# Headingin each file (if present) is used as the resource title; otherwise the filename stem is used. - Set
AIRFLOW_MCP_RESOURCES_DIR=/path/to/docsif you prefer environment-based configuration. - Update the files on disk and restart the server to refresh the resources list.
Considerations
Authentication
- Only JWT authentication is supported in Airflow 3.0. You must provide a valid
AUTH_TOKEN.
Page Limit
The default is 100 items, but you can change it using maximum_page_limit option in [api] section in the airflow.cfg file.
Transport Selection
- Use stdio transport for direct process communication (default)
- Use HTTP transport for web deployments, multiple clients, or when you need better scalability
- Avoid SSE transport as it's deprecated in favor of HTTP transport
Related MCP servers
Read-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.
Agent-native catalogue of Baseframe Labs dev tools and MCP servers.
Agent-first MCP. 11 AST adapters, 12 named languages, 51 tools, mission outcomes. Local.

abm.dev — the account-based marketing API for AI agents: Search, Enrich, and Create across B2B.

