What is the key difference between Airflow MCP Server and MCP Databricks Server?

Airflow MCP Server belongs to the Data Platforms category with local stdio execution, while MCP Databricks Server belongs to the Data Platforms category with local stdio execution.

How do I install Airflow MCP Server or MCP Databricks Server in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are Airflow MCP Server and MCP Databricks Server free or paid?

Airflow MCP Server operates under a Free / Open Source model (other). MCP Databricks Server operates under a Free / Open Source model (API Key required).

Which MCP server has more tools and community activity?

Airflow MCP Server lists 7 tools with 3 views and 2 GitHub stars. MCP Databricks Server lists 5 tools with 3 views and 50 GitHub stars.

Can I use both Airflow MCP Server and MCP Databricks Server together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

Side-by-Side Model Context Protocol Comparison

Airflow MCP Server vs MCP Databricks Server

In-depth architectural comparison of the Airflow MCP Server and MCP Databricks Server MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

At a Glance & Executive Verdict

Airflow MCP Server

Data Platforms · Local stdio

Quality: 60/100 (Good) | Auth: other

MCP Databricks Server

Data Platforms · Local stdio

Quality: 35/100 (Fair) | Auth: API Key required

Verdict Summary: Choose Airflow MCP Server if you need specialized Data Platforms tools running via a local process. Choose MCP Databricks Server if your workspace requires Data Platforms integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose Airflow MCP Server when:

You need dedicated capabilities in the Data Platforms domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: other (Free / Open Source).
You have access to required keys: AIRFLOW_API_URL, AIRFLOW_USERNAME, AIRFLOW_PASSWORD, AIRFLOW_ALLOW_WRITE, AIRFLOW_TOOLS, AIRFLOW_DISABLE.
Primary tools included: airflow-list-dags, airflow-list-runs, airflow-get-task-instances.

Explore Airflow MCP Server Details

Choose MCP Databricks Server when:

You need dedicated capabilities in the Data Platforms domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Free / Open Source).
You have access to required keys: DATABRICKS_HOST, DATABRICKS_TOKEN, DATABRICKS_HTTP_PATH.

Feature & Specification Comparison

Specification	Airflow MCP Server us-all Data Platforms	MCP Databricks Server JordiNei Data Platforms
Summary	Airflow REST API — 7 tools (DAG list, runs, task instances, log tails, trigger, clear). dag-health-rollup aggregation. Airflow 3.x /api/v2 + JWT (SimpleAuthManager); pin 0.1.x for Airflow 2.x. Read-only by default; trigger/clear write-gated.	Connect to Databricks API, allowing LLMs to run SQL queries, list jobs, and get job status.
Category & Scope

Tools & Capabilities Breakdown

Airflow MCP Server Tools (7)

airflow-list-dags

List active DAGs with tag/search filters

airflow-list-runs

Recent runs of one DAG (state filter, ordered newest first)

airflow-get-task-instances

Task instances for a specific DAG run

airflow-get-task-logs

Tail (last N kB) of one task instance log

airflow-trigger-dag

Trigger a new run (write-gated)

airflow-clear-task

Clear specific task instances → re-run (write-gated)

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

Airflow MCP Server Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "us-all-airflow-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@us-all/airflow-mcp"
      ],
      "env": {
        "AIRFLOW_API_URL": "YOUR_AIRFLOW_API_URL_HERE",
        "AIRFLOW_USERNAME": "YOUR_AIRFLOW_USERNAME_HERE",
        "AIRFLOW_PASSWORD": "YOUR_AIRFLOW_PASSWORD_HERE",
        "AIRFLOW_ALLOW_WRITE": "YOUR_AIRFLOW_ALLOW_WRITE_HERE",
        "AIRFLOW_TOOLS": "YOUR_AIRFLOW_TOOLS_HERE",
        "AIRFLOW_DISABLE": "YOUR_AIRFLOW_DISABLE_HERE"
      }
    }
  }
}

MCP Databricks Server Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "jordinei-mcp-databricks-server": {
      "command": "npx",
      "args": [
        "-y",
        "jordinei-mcp-databricks-server"
      ],
      "env": {
        "DATABRICKS_HOST": "YOUR_DATABRICKS_HOST_HERE",
        "DATABRICKS_TOKEN": "YOUR_DATABRICKS_TOKEN_HERE",
        "DATABRICKS_HTTP_PATH": "YOUR_DATABRICKS_HTTP_PATH_HERE"
      }
    }
  }
}

Frequently Asked Questions

Airflow MCP Server is categorized under Data Platforms and uses a local stdio subprocess. In contrast, MCP Databricks Server belongs to Data Platforms using local stdio subprocess. Select Airflow MCP Server when you need capabilities focused on data platforms and MCP Databricks Server when you require tools for data platforms.

More alternatives to Airflow MCP Server More alternatives to MCP Databricks Server Data Platforms category hub Canonical compare URL