This server provides tools to interact with Airflow 3.x via its REST API, enabling both read access and write-gated actions for DAG and task management.
Core Tools
airflow-list-dags: Browse active DAGs with optional tag filtering, DAG ID substring search, and paused DAG exclusion.
airflow-list-runs: Retrieve recent runs for a specific DAG, filterable by state (success, failed, running, etc.), ordered newest first.
airflow-get-task-instances: Inspect all task instances within a DAG run, including state, try number, and duration.
airflow-get-task-logs: Tail the last N kilobytes of a task instance's log for a specific try number — useful for debugging failures.
dag-health-rollup: Aggregated health summary for a DAG including success rate, run count breakdown, average duration, last failed run, and failing task instances.
airflow-trigger-dag (requires AIRFLOW_ALLOW_WRITE=true): Trigger a new DAG run with optional conf payload, note, and logical date.
airflow-clear-task (requires AIRFLOW_ALLOW_WRITE=true): Clear specific task instances to force re-execution, with optional upstream/downstream inclusion.
search-tools: Discover available tools via natural language queries.
Pre-built Prompts / Workflows
dag-failure-triage: Guided workflow to diagnose DAG failures — pulls runs, isolates the failure, dumps logs, and proposes remediation.
dag-schedule-audit: Sweeps all DAGs to identify those with low success rates or stuck runs.
Auth & Transport
Authenticates via JWT (SimpleAuthManager) using AIRFLOW_USERNAME and AIRFLOW_PASSWORD; tokens are auto-refreshed.
Supports stdio (default) or Streamable HTTP transport (MCP_TRANSPORT=http).
Compatible with Claude Desktop, Cursor, and any MCP client.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@airflow-mcp-server list all active DAGs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
pnpm add -D @us-all/airflow-mcpRelated MCP server: Apache Airflow MCP Server
AIRFLOW_API_URL=http://airflow.example.com:8080 \
AIRFLOW_USERNAME=admin AIRFLOW_PASSWORD=... \
npx @us-all/airflow-mcpPass 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).
airflow (6 + 1 aggregation)Tool | Description |
| List active DAGs with tag/search filters |
| Recent runs of one DAG (state filter, ordered newest first) |
| Task instances for a specific DAG run |
| Tail (last N kB) of one task instance log |
| Trigger a new run (write-gated) |
| Clear specific task instances → re-run (write-gated) |
| Aggregated DAG health: success rate + avg duration + last failed run + failing tasks |
metasearch-tools — natural-language tool discovery.
Prompt | Use when |
| "Why did DAG X fail?" — pulls runs, isolates failure, dumps logs, proposes remediation |
| "Sweep all DAGs for low success rate and stuck runs" |
Env | Required | Notes |
| yes | Airflow host base, e.g. |
| yes | Username for JWT minting via SimpleAuthManager |
| yes | Password for JWT minting (secret) |
| no |
|
| no | Category toggles |
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.
For dbt artifact parsing, run-results history, and DQ result tables, install @us-all/dbt-mcp alongside.
pnpm install
pnpm run build # tsc → dist/
pnpm test # vitest
pnpm run smoke # spawns dist/index.js, calls initialize + tools/list (set env first)MIT — see LICENSE.
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.
List task instances for a specific Airflow DAG run with state, try_number, duration
Inputs: dagId (required), dagRunId (required), extractFields.
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.
List Airflow DAGs (active by default) with optional tag filter and dag_id substring search
Inputs: onlyActive, tag, search, limit, +1 more.
List recent runs of one Airflow DAG, optionally filtered by state, ordered newest first
Inputs: dagId (required), state, limit, extractFields.
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.
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.
Discover available Airflow MCP tools by natural language query.
Inputs: query (required), category, limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
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.
