airflow-mcp-server
@us-all/airflow-mcp
Airflow MCP 서버 — DAG, 실행, 태스크 인스턴스, 로그 테일 읽기; 트리거 및 초기화(쓰기 제한).
@us-all/mcp-toolkit기반으로 구축되었습니다.
Airflow Stable REST API를 위한 집중형 MCP입니다. 기본적으로 읽기 전용이며, airflow-trigger-dag 및 airflow-clear-task는 AIRFLOW_ALLOW_WRITE=true로 설정해야 사용할 수 있습니다.
더 깊은 dbt 통합(매니페스트 파싱, 실행 결과 기록, 소스 신선도, 컬럼별 테스트 커버리지, 리니지 추적, 사용자 정의 DQ 결과 테이블)을 원하시면 동반 패키지인 **@us-all/dbt-mcp**를 함께 설치하세요.
airflow+meta카테고리의 7개 도구DAG 트리아주 워크플로우를 위한 2개의 MCP 프롬프트
list-runs → get-task-instances 조합을 대체하는 1개의 집계 도구
설치
pnpm add -D @us-all/airflow-mcpRelated MCP server: Apache Airflow MCP Server
실행
AIRFLOW_API_URL=http://airflow.example.com:8080/api/v1 \
AIRFLOW_USERNAME=admin AIRFLOW_PASSWORD=... \
npx @us-all/airflow-mcp이 서버는 MCP stdio를 사용하며, Claude Desktop / Cursor / 기타 MCP 클라이언트에 연결할 수 있습니다. MCP_TRANSPORT=http를 설정하여 스트리밍 가능한 HTTP 전송(Bearer 인증, /health 엔드포인트)을 선택할 수 있습니다.
도구
airflow (6개 + 1개 집계)
도구 | 설명 |
| 태그/검색 필터가 적용된 활성 DAG 목록 |
| 특정 DAG의 최근 실행 목록 (상태 필터, 최신순 정렬) |
| 특정 DAG 실행에 대한 태스크 인스턴스 |
| 특정 태스크 인스턴스 로그의 테일(마지막 N kB) |
| 새 실행 트리거 (쓰기 제한) |
| 특정 태스크 인스턴스 초기화 → 재실행 (쓰기 제한) |
| 집계된 DAG 상태: 성공률 + 평균 소요 시간 + 마지막 실패 실행 + 실패한 태스크 |
meta
search-tools — 자연어 도구 검색.
프롬프트
프롬프트 | 사용 시기 |
| "DAG X가 왜 실패했는가?" — 실행 내역을 가져오고, 실패 원인을 격리하며, 로그를 덤프하고, 해결책을 제안 |
| "낮은 성공률과 멈춘 실행이 있는 모든 DAG를 검사" |
환경 변수
환경 변수 | 필수 | 참고 |
| 예 | Airflow REST API 기본 URL, 예: |
| 아니오 | 기본 인증 사용자 이름 |
| 아니오 | 기본 인증 비밀번호 (보안) |
| 아니오 |
|
| 아니오 | 카테고리 토글 |
테스트된 스키마
Airflow Stable REST API (2.x). Airflow 3.x는
/api/v1/Stable 엔드포인트를 통해 동일한 인터페이스를 제공하므로, 이 서버는 2.x 및 3.x 배포 환경 모두에서 작동합니다.
동반 서버
dbt 아티팩트 파싱, 실행 결과 기록 및 DQ 결과 테이블을 사용하려면 @us-all/dbt-mcp를 함께 설치하세요.
빌드
pnpm install
pnpm run build # tsc → dist/
pnpm test # vitest
pnpm run smoke # spawns dist/index.js, calls initialize + tools/list (set env first)라이선스
MIT — LICENSE를 참조하세요.
Available Tools
8 toolsairflow-clear-taskA
Clear specific task instances in an Airflow DAG run (re-run them); supports include_upstream / include_downstream. Write-gated by AIRFLOW_ALLOW_WRITE.
Inputs: dagId (required), dagRunId (required), taskIds (required), includeDownstream, +1 more.
airflow-get-task-instancesB
List task instances for a specific Airflow DAG run with state, try_number, duration
Inputs: dagId (required), dagRunId (required), extractFields.
airflow-get-task-logsB
Fetch the tail (last N kB) of an Airflow task instance log for a specific try_number
Inputs: dagId (required), dagRunId (required), taskId (required), tryNumber, +2 more.
airflow-list-dagsB
List Airflow DAGs (active by default) with optional tag filter and dag_id substring search
Inputs: onlyActive, tag, search, limit, +1 more.
airflow-list-runsA
List recent runs of one Airflow DAG, optionally filtered by state, ordered newest first
Inputs: dagId (required), state, limit, extractFields.
airflow-trigger-dagA
Trigger a new Airflow DAG run with optional conf payload and note. Write-gated by AIRFLOW_ALLOW_WRITE.
Inputs: dagId (required), dagRunId, conf, note, +1 more.
dag-health-rollupA
Aggregated DAG health: success-rate over the last N runs + count breakdown (succeeded/failed/queued) + average duration + last-failed-run id + (optional) failing task instances. Replaces the airflow-list-runs + airflow-get-task-instances combo for 'is this DAG healthy right now?'.
Inputs: dagId (required), recentRuns, includeFailingTasks, extractFields.
search-toolsA
Discover available Airflow MCP tools by natural language query.
Inputs: query (required), category, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool maps to a distinct resource/action: DAGs, runs, task instances, logs, aggregate health, and tool discovery. dag-health-rollup and airflow-list-runs could overlap for health questions, but the description explicitly positions the rollup as the higher-level replacement, so ambiguity remains low.
Most tools follow the airflow-<verb>-<object> pattern (airflow-list-dags, airflow-trigger-dag, airflow-clear-task, airflow-list-runs, airflow-get-task-instances, airflow-get-task-logs), but dag-health-rollup and search-tools break both the airflow- prefix and the verb-noun convention. There is also minor inconsistency between 'list' and 'get' for similar retrieval operations.
Eight tools is well-scoped for an Airflow operations server. Each tool covers a meaningful operation without redundancy or bloat.
The set covers the core operational workflow: discover DAGs, trigger runs, inspect runs/task instances/logs, clear tasks, and get an aggregated health rollup. Minor gaps like pause/unpause DAGs or fetching DAG details exist, but they do not break the primary monitoring and troubleshooting use case.
Maintenance
Related MCP Connectors
Official Airtable MCP server — database and operations layer for agents.
Streamable HTTP MCP server exposing planner flows, tasks, and squads.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
Argentic MCP server: run and inspect long-running agents on Argentic.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables inspection and management of Apache Airflow DAGs, runs, and logs across multiple instances. It provides tools for monitoring workflows and performing gated write operations like triggering DAGs or clearing task instances.1673 PyPI2Apache 2.0
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that wraps the Apache Airflow REST API, enabling clients to manage DAGs, monitor task instances, and handle workflows through a standardized interface. It provides comprehensive access to Airflow features including DAG runs, variables, connections, and XComs.MIT
- AlicenseAqualityCmaintenanceMCP server exposing Apache Airflow REST API operations as tools — list DAGs, inspect runs and task instances, trigger DAG runs, and check failed DAGs and scheduler health72MIT
- FlicenseNot gradedqualityDmaintenanceEnables DAG management, monitoring, debugging, and connection testing for Apache Airflow through the MCP protocol.-