Incident Response MCP for Apache Airflow

Apache Airflow MCP Server

Independent community project; not affiliated with or endorsed by the Apache Software Foundation.

Published through PyPI, GHCR, and the official MCP Registry. Reproducible scan reports, dependency audits, SBOMs, and provenance are attached to each immutable release.

Connect Claude, Cursor, VS Code, or another MCP client to your Apache Airflow deployments and help agents diagnose failed DAGs.

Paste an Airflow UI link from a PagerDuty/Datadog alert and ask *"why did this fail?"* — the agent resolves the URL, finds the failed tasks, pulls log errors filtered and bounded before the MCP response, and can re-trigger or clear runs. Write tools carry destructive-operation annotations that MCP clients can use to request confirmation.

Highlights

• 🔍 Incident-response first — resolve Airflow UI URLs straight to the failing task, filter logs by error level with context lines, follow try_number semantics correctly (sensors included)
• 🏢 Multi-instance — one server for same-API-family dev/staging/prod targets, with per-instance credentials and an SSRF guard that rejects unknown hosts
• 🔒 Safety controls — opt-in read-only mode (AIRFLOW_MCP_READ_ONLY=true) that never registers write tools; write tools annotated as destructive; configured credentials are redacted from instance responses and operation logs
• 📉 Token-efficient — log tailing, level filtering, byte caps, and truncation metadata designed for LLM context windows
• 🧭 Airflow 2 and 3 — API v1/v2 adapters with live E2E against Airflow 2.11 and 3.3, including JWT auth
• 📎 Traceable — every response carries a request_id that matches the structured server logs

Quickstart

1. Install

uv tool install apache-airflow-mcp-server \

--with 'apache-airflow-client==3.3.0' # replace 3.3.0 with your Airflow version

Airflow 2.11? Use --with 'apache-airflow-client==2.10.0' instead; 2.10.0 is the final generated v1 client and targets Airflow 2's stable API. See Airflow compatibility before using a different release.

2. Connect your MCP client

The fastest path is a single instance configured entirely with environment variables — no config file needed.

Claude Code

claude mcp add airflow \

--env AIRFLOW_MCP_HOST=https://airflow.example.com \ --env AIRFLOW_MCP_USERNAME=admin \ --env AIRFLOW_MCP_PASSWORD=your-password \ --env AIRFLOW_MCP_READ_ONLY=true \ -- uvx --from apache-airflow-mcp-server \ --with apache-airflow-client==3.3.0 airflow-mcp --transport stdio

</details>

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

{

"mcpServers": { "airflow": { "command": "uvx", "args": ["--from", "apache-airflow-mcp-server", "--with", "apache-airflow-client==3.3.0", "airflow-mcp", "--transport", "stdio"], "env": { "AIRFLOW_MCP_HOST": "https://airflow.example.com", "AIRFLOW_MCP_USERNAME": "admin", "AIRFLOW_MCP_PASSWORD": "your-password", "AIRFLOW_MCP_READ_ONLY": "true" } } } }

</details>

Cursor

Add to ~/.cursor/mcp.json:

{

"mcpServers": { "airflow": { "command": "uvx", "args": ["--from", "apache-airflow-mcp-server", "--with", "apache-airflow-client==3.3.0", "airflow-mcp", "--transport", "stdio"], "env": { "AIRFLOW_MCP_HOST": "https://airflow.example.com", "AIRFLOW_MCP_USERNAME": "admin", "AIRFLOW_MCP_PASSWORD": "your-password", "AIRFLOW_MCP_READ_ONLY": "true" } } } }

</details>

VS Code (Copilot)

Add to .vscode/mcp.json:

{

"servers": { "airflow": { "type": "stdio", "command": "uvx", "args": ["--from", "apache-airflow-mcp-server", "--with", "apache-airflow-client==3.3.0", "airflow-mcp", "--transport", "stdio"], "env": { "AIRFLOW_MCP_HOST": "https://airflow.example.com", "AIRFLOW_MCP_USERNAME": "admin", "AIRFLOW_MCP_PASSWORD": "your-password", "AIRFLOW_MCP_READ_ONLY": "true" } } } }

</details>

Any client, over HTTP

Run the server yourself and point the client at the endpoint:

AIRFLOW_MCP_HOST=https://airflow.example.com \

AIRFLOW_MCP_USERNAME=admin AIRFLOW_MCP_PASSWORD=your-password \ AIRFLOW_MCP_READ_ONLY=true \ airflow-mcp --transport http --host 127.0.0.1 --port 8765

{ "mcpServers": { "airflow": { "url": "http://127.0.0.1:8765/mcp" } } }

Health check: GET /health → 200 OK.

3. Ask your agent something

*"Why did the latest run of etl_pipeline fail?"*

*"https://airflow.example.com/dags/etl_pipeline/grid — what happened here, and is it safe to clear?"*

*"Show the failed task's error context and tell me the smallest recovery action."*

Airflow compatibility

The server talks to Airflow through the generated apache-airflow-client. For Airflow 3, match the client release to your Airflow release: generated models can change within a major version, and a newer client is not guaranteed to deserialize an older server's responses correctly. Airflow 2.11 uses the final v1 client release, 2.10.0, against Airflow 2's stable API.

When api_version isn't set, the server assumes the API matching the installed client (v1 for a 2.x client, v2 for 3.x). Set AIRFLOW_MCP_API_VERSION (or api_version: in the registry) explicitly to catch a major-version mismatch early.

One server process can currently load only one generated client major. All instances in a registry must therefore use the same API family; run separate MCP server processes for Airflow 2 and Airflow 3. Mixed-version support requires a future client-adapter change and is not advertised as working today.

Airflow 3 notes:

• Auth: bearer tokens are passed through as JWTs; basic credentials are automatically exchanged for a JWT via POST /auth/token and refreshed periodically (AIRFLOW_MCP_TOKEN_REFRESH_SECONDS, default 3600 — keep it below your deployment's JWT expiry, and note there is no automatic re-auth on 401 yet).
• execution_date ordering maps to logical_date, datasets map to assets, and UI links use the Airflow 3 route scheme. Tool names and the core workflow stay stable; documented fields and options can differ by API family.
• Clear options that no longer exist in Airflow 3 (include_subdags/include_parentdag, and the include_*/reset_dag_runs options of airflow_clear_dag_run) are rejected with INVALID_INPUT rather than silently narrowing a destructive operation.

Both client families are exercised on relevant pull requests and main pushes. Bug reports from real Airflow deployments are very welcome!

Configuration

Single instance (env vars only)

\* provide either username+password or a token.

Multiple instances (registry YAML)

Point AIRFLOW_MCP_INSTANCES_FILE at a YAML registry (it takes precedence over the single-instance env vars). Values may reference environment variables with ${VAR}:

data-stg:

host: https://airflow.data-stg.example.com/ api_version: v1 # Airflow 2 verify_ssl: true auth: type: basic username: ${AIRFLOW_DATA_STG_USERNAME} password: ${AIRFLOW_DATA_STG_PASSWORD}

data-prod: host: https://airflow.data-prod.example.com/ api_version: v1 # Keep one client/API family per server process auth: type: bearer token: ${AIRFLOW_DATA_PROD_TOKEN}

Every tool accepts either an instance key (data-stg) or a ui_url — a full http(s) Airflow UI URL whose host is resolved against the registry, with unknown hosts rejected (SSRF guard). ui_url also auto-fills dag_id/dag_run_id/task_id when the link contains them. If both instance and ui_url are passed and disagree, the call fails with INSTANCE_MISMATCH rather than guessing.

Kubernetes tip: mount the registry from a Secret at /config/instances.yaml and set AIRFLOW_MCP_INSTANCES_FILE=/config/instances.yaml.

Server options

Read-only mode

The quickstarts set AIRFLOW_MCP_READ_ONLY=true: write tools (trigger, clear, pause/unpause) are never registered. This prevents MCP mutations, but read tools can still disclose sensitive logs, configuration, rendered fields, and DAG-run data; use least-privilege Airflow credentials.

To enable recovery operations deliberately, set AIRFLOW_MCP_READ_ONLY=false. Write tools then carry MCP destructiveHint annot