Airflow

airflow-mcp-server: An MCP Server for controlling Airflow 3

mcp-name: io.github.abhishekbhakat/airflow-mcp-server

This MCP server is certified byMCPHub. This certification ensures that airflow-mcp-server follows best practices for Model Context Protocol implementation.

AModel Context Protocolserver for controlling Airflow via Airflow APIs.

https://github.com/user-attachments/assets/f3e60fff-8680-4dd9-b08e-fa7db655a705

{ "mcpServers": { "airflow-mcp-server": { "command": "uvx", "args": [ "airflow-mcp-server", "--base-url", "http://localhost:8080", "--auth-token", "<jwt_token>" ] } } }

SeeCONFIG.mdfor IDE-specific configuration examples across popular MCP clients.

{ "mcpServers": { "airflow-mcp-server-http": { "command": "uvx", "args": [ "airflow-mcp-server", "--http", "--port", "3000", "--base-url", "http://localhost:8080", "--auth-token", "<jwt_token>" ] } } }

The server supports multiple transport protocols:

Standard input/output transport for direct process communication:

airflow-mcp-server --safe --base-url http://localhost:8080 --auth-token <jwt>

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.

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 explicitly start in unsafe mode (though this is default):

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.

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.

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.
- SetAIRFLOW_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.

- Only JWT authentication is supported in Airflow 3.0. You must provide a validAUTH_TOKEN.

The default is 100 items, but you can change it usingmaximum_page_limitoption in [api] section in theairflow.cfgfile.

- Usestdiotransport for direct process communication (default)
- UseHTTPtransport for web deployments, multiple clients, or when you need better scalability
- AvoidSSEtransport as it's deprecated in favor of HTTP transport

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Orchestration tool for managing multiple MCP servers with a Docker Compose-style interface and a unified HTTP proxy.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

One remote MCP server for 500+ production APIs — Stripe, HubSpot, Postgres, Gmail, and more. OAuth and API key auth, credential management, and a CLI.

Single tool to control all 100+ API integrations, and UI components

Interact with your MLOps and LLMOps pipelines through your ZenML MCP server

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

Provides tools to interact with the Ansible Automation Platform API for automation tasks.

Self-hosted MCP gateway: convert REST/SOAP/GraphQL/SQL APIs into MCP tools with 29 pre-built adapters, OAuth2, RBAC and audit log.