Log inSubmit server
Incident Response MCP for Apache Airflow logo

Incident Response MCP for Apache Airflow

Diagnoses Airflow failures from UI links, bounded logs, and optional recovery operations.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Incident Response MCP for Apache Airflow

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "incident-response-mcp-for-apache-airflow": {
      "command": "uvx",
      "args": [
        "--from",
        "apache-airflow-mcp-server",
        "--with",
        "apache-airflow-client==3.3.0",
        "airflow-mcp"
      ],
      "env": {
        "AIRFLOW_MCP_HOST": "YOUR_VALUE_HERE",
        "AIRFLOW_MCP_USERNAME": "YOUR_VALUE_HERE",
        "AIRFLOW_MCP_PASSWORD": "YOUR_VALUE_HERE",
        "AIRFLOW_MCP_API_VERSION": "YOUR_VALUE_HERE",
        "AIRFLOW_MCP_READ_ONLY": "YOUR_VALUE_HERE",
        "AIRFLOW_MCP_TOKEN_REFRESH_SECONDS": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Incident Response MCP for Apache Airflow MCP server connects MCP clients to Apache Airflow deployments through the Airflow REST API. It resolves UI URLs, inspects DAGs, runs, task attempts, and bounded logs, then can trigger, clear, or pause resources when write access is enabled. Use it for incident triage across same-API-family Airflow instances, especially when an alert includes an Airflow link. Read-only mode prevents write tools from being registered.

Use cases

  • Investigate failed DAG runs from Airflow UI links
  • Inspect bounded task logs during incident triage
  • Trigger or clear Airflow runs after review
  • Compare DAG and task state across configured instances

Key features

  • Resolve Airflow UI URLs into run and task identifiers
  • Filter and bound task-instance logs
  • Support Airflow 2 and Airflow 3 API families
  • Configure multiple same-family Airflow instances
  • Offer read-only mode and destructive-operation annotations
  • Trigger, clear, and pause Airflow resources

Tools15

What Incident Response MCP for Apache Airflow lets your agent do. Expand a tool for its parameters.

Self-reported~257 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

7/7 checks healthy over the last 39d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9h ago via OSV.dev · apache-airflow-mcp-server (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Tools exposed15Callable tools this server registers over MCP.

How Incident Response MCP for Apache Airflow works

What Incident Response MCP for Apache Airflow does

Incident Response MCP for Apache Airflow MCP server exposes Apache Airflow operations as MCP tools for clients such as Claude, Cursor, and VS Code. Its workflow is centered on investigating failed DAG runs: provide an Airflow UI URL, resolve its instance and identifiers, inspect the related run and task attempts, and retrieve bounded log output.

The server supports multiple configured Airflow instances when they use the same API family. Instance descriptions include the host, API version, and authentication type, while secrets are redacted from responses and operation logs. Responses also include a request ID that can be matched with structured server logs.

How it works

The server communicates with Airflow through the generated apache-airflow-client. Airflow 2 uses the v1 API client, while Airflow 3 uses the v2 client. The installed client version should match the deployed Airflow version, particularly for Airflow 3, where generated models may change within a major release.

An agent can resolve an Airflow UI link into an instance, DAG, run, and task reference. It can then list or retrieve DAG runs and task instances, filter task instances by state or task ID, and inspect retries, timings, metadata, and optionally rendered template fields. Log retrieval supports level filtering, tailing, context lines, byte limits, and truncation metadata to keep responses bounded.

The Incident Response MCP for Apache Airflow MCP server also applies an SSRF guard that rejects unknown hosts. Airflow 3 deployments can use bearer JWTs; basic credentials are exchanged for a JWT and refreshed periodically.

Setup and configuration

Install the package with uv tool install or run it through uvx, adding an Airflow client version that matches the target deployment. Configure a single instance with environment variables, or use the server's multi-instance configuration described by the project. The server can run over stdio or HTTP; the HTTP example listens locally and exposes /mcp, with /health available for a health check.

Relevant environment variables include:

  • AIRFLOW_MCP_HOST for the Airflow base URL.
  • AIRFLOW_MCP_USERNAME and AIRFLOW_MCP_PASSWORD for basic credentials.
  • AIRFLOW_MCP_API_VERSION to select v1 or v2 explicitly.
  • AIRFLOW_MCP_READ_ONLY=true to omit write tools.
  • AIRFLOW_MCP_TOKEN_REFRESH_SECONDS to control JWT refresh timing.

For Airflow 2.11, the documented client is apache-airflow-client==2.10.0. For Airflow 3.3, the documented client is apache-airflow-client==3.3.0.

Tools and capabilities

The tool set includes instance discovery and description, UI URL parsing, DAG listing and retrieval, DAG-run listing and retrieval, task-instance inspection, and dataset or asset event queries. Task logs can be narrowed before they reach the MCP response.

Recovery and scheduling operations include triggering a DAG with optional configuration, logical date, or note; clearing selected task instances; clearing an entire DAG run; and toggling DAG pause state. Clear operations default to dry_run=true. Write tools carry destructive-operation annotations that MCP clients can use when requesting confirmation.

Limitations and notes

A single server process loads only one generated client major, so all configured instances must use the same API family. Run separate processes for Airflow 2 and Airflow 3. Airflow 3.0 through 3.2 and Airflow 2.5 through 2.10 are not in the current live compatibility matrix.

For Airflow 3, token refresh does not automatically re-authenticate after a 401 response. The refresh interval should remain below the deployment's JWT expiry. API-specific fields and options can differ; unsupported Airflow 3 clear options are rejected rather than silently narrowed. The project is an independent community project and is not affiliated with or endorsed by the Apache Software Foundation.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Incident Response MCP for Apache Airflow

Incident Response MCP for Apache Airflow is an MCP server that connects AI clients to Apache Airflow deployments through their REST APIs. Its main tools resolve UI URLs, inspect DAGs, runs, and task instances, retrieve bounded logs, and optionally trigger, clear, or pause Airflow resources.

Install it with `uv tool install apache-airflow-mcp-server` and add the generated Airflow client matching your deployment. You can also run it with `uvx`, configure environment variables, and connect an MCP client over stdio or HTTP.

Yes, it works with Cursor through a stdio MCP configuration. Add the server command and Airflow connection variables to `~/.cursor/mcp.json`; the documented setup uses `uvx` and an Airflow client version matching the deployment.

Yes, set `AIRFLOW_MCP_READ_ONLY=true` to prevent write tools from being registered. Read operations such as DAG inspection, task lookup, and bounded log retrieval remain available, while triggering, clearing, and pausing operations are omitted.

It has live end-to-end coverage for Airflow 2.11 and 3.3. Airflow 2 uses the v1 client and Airflow 3 uses the v2 client; other versions are not in the current live matrix and require matching client compatibility.

Related MCP servers

All in Data Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewIncident Response MCP for Apache Airflow AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/incident-response-mcp-for-apache-airflow?style=directory)](https://allmcps.com/mcp/incident-response-mcp-for-apache-airflow)
HTML Embed
<a href="https://allmcps.com/mcp/incident-response-mcp-for-apache-airflow"><img src="https://allmcps.com/api/badge/incident-response-mcp-for-apache-airflow?style=directory" alt="Incident Response MCP for Apache Airflow on AllMCPs" /></a>