convez.ai
MCP ServerAutomaçãoIntermediário
us-all

Airflow MCP Server

us-all/airflow-mcp-server

Integração MCP para gerenciar DAGs, runs e tasks do Airflow

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP para integração com Apache Airflow 3.x via REST API. Permite listar DAGs, execuções, instâncias de tarefas, logs em tempo real, além de disparar e limpar execuções com controle de acesso. Autentica via JWT e oferece ferramentas de triage de falhas e auditoria de agendamento.

Instalação

$npx convez-ai us-all/airflow-mcp-server

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2
Forks
0
Acompanhando
0
Saúde
75%
Último commit
há 4 meses
Versão
v1.4.1
Issues abertas
0
Contribuidores
1

Casos de uso

  • Investigar e resolver falhas em pipelines Airflow
  • Monitorar saúde agregada de DAGs (taxa de sucesso, duração média)
  • Disparar novas execuções e limpar tasks específicas
  • Auditar agendamento e taxa de sucesso de todos os DAGs
  • Consultar logs de instâncias de tarefas para diagnóstico

Veredito

MCP bem arquitetado para quem trabalha com Airflow 3.x em produção. A separação entre leitura por padrão e escrita com feature flag é prudente; os prompts prontos para triage de falhas e auditoria agregam valor real. Requer Airflow 3.0+, não compatível com 2.x.

README

A tradução para o português deste README ainda está na fila.

@us-all/airflow-mcp

Airflow MCP server — read DAGs, runs, task instances, log tails; trigger and clear (write-gated). Built on @us-all/mcp-toolkit.

A focused MCP for the Airflow 3.x REST API (/api/v2). Read by default; airflow-trigger-dag and airflow-clear-task are gated behind AIRFLOW_ALLOW_WRITE=true. Auth is JWT via SimpleAuthManager — supply AIRFLOW_USERNAME + AIRFLOW_PASSWORD and the server mints/refreshes the token transparently.

For deeper dbt integration (manifest parsing, run-results history, source freshness, per-column test coverage, lineage walks, custom DQ result tables), install the companion @us-all/dbt-mcp alongside.

  • 7 tools in airflow + meta categories
  • 2 MCP Prompts for DAG triage workflows
  • 1 aggregation tool that replaces the list-runs → get-task-instances combo

Install

pnpm add -D @us-all/airflow-mcp

Run

AIRFLOW_API_URL=http://airflow.example.com:8080 \
AIRFLOW_USERNAME=admin AIRFLOW_PASSWORD=... \
npx @us-all/airflow-mcp

Pass the host base only — the server prepends /api/v2 internally. A trailing /api/v1 or /api/v2 is stripped if supplied. JWT tokens are cached for the lifetime of the session and refreshed 1 minute before they expire.

The server speaks MCP stdio; wire it into Claude Desktop / Cursor / any MCP client. Set MCP_TRANSPORT=http to opt in to Streamable HTTP transport (Bearer auth, /health endpoint).

Tools

airflow (6 + 1 aggregation)

ToolDescription
airflow-list-dagsList active DAGs with tag/search filters
airflow-list-runsRecent runs of one DAG (state filter, ordered newest first)
airflow-get-task-instancesTask instances for a specific DAG run
airflow-get-task-logsTail (last N kB) of one task instance log
airflow-trigger-dagTrigger a new run (write-gated)
airflow-clear-taskClear specific task instances → re-run (write-gated)
dag-health-rollupAggregated DAG health: success rate + avg duration + last failed run + failing tasks

meta

search-tools — natural-language tool discovery.

Prompts

PromptUse when
dag-failure-triage"Why did DAG X fail?" — pulls runs, isolates failure, dumps logs, proposes remediation
dag-schedule-audit"Sweep all DAGs for low success rate and stuck runs"

Environment variables

EnvRequiredNotes
AIRFLOW_API_URLyesAirflow host base, e.g. http://airflow.example.com:8080. Trailing /api/v1 or /api/v2 is stripped if present
AIRFLOW_USERNAMEyesUsername for JWT minting via SimpleAuthManager /auth/token
AIRFLOW_PASSWORDyesPassword for JWT minting (secret)
AIRFLOW_ALLOW_WRITEnotrue enables airflow-trigger-dag / airflow-clear-task
AIRFLOW_TOOLS / AIRFLOW_DISABLEnoCategory toggles

Tested-against schemas

  • Airflow 3.0–3.2 /api/v2 (verified against 3.2.1, current Airflow release as of 2026-05). Airflow 2.x is not supported by v0.2+ because basic auth + /api/v1 were removed; pin to @us-all/airflow-mcp@0.1.0 for Airflow 2.x deployments.

Companion server

For dbt artifact parsing, run-results history, and DQ result tables, install @us-all/dbt-mcp alongside.

Build

pnpm install
pnpm run build      # tsc → dist/
pnpm test           # vitest
pnpm run smoke      # spawns dist/index.js, calls initialize + tools/list (set env first)

License

MIT — see LICENSE.

Ver o original no GitHub

Bom para

Relacionados