Airflow runs on your own machine — the client starts it, so there is no endpoint to ping. 80 installs a week from npm. Last commit 10 Jul 2026.
Airflow MCP — list DAGs/runs/task instances, tail logs, trigger and clear (write-gated)
Today is the operative word: we check Airflow every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add airflow -- npx -y @us-all/airflow-mcp
{
"mcpServers": {
"airflow": {
"args": [
"-y",
"@us-all/airflow-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.airflow]
command = "npx"
args = ["-y", "@us-all/airflow-mcp"]
{
"mcpServers": {
"airflow": {
"args": [
"-y",
"@us-all/airflow-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"airflow": {
"args": [
"-y",
"@us-all/airflow-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AIRFLOW_API_URL (Airflow host base, e.g. 'http://airflow.example.com:8080'. Server prepends /api/v2 internally; trailing /api/v1 or /api/v2 is stripped if supplied.), AIRFLOW_USERNAME (Airflow username (used to mint a JWT via SimpleAuthManager /auth/token).), AIRFLOW_PASSWORD (Airflow password (used to mint a JWT via SimpleAuthManager /auth/token).), AIRFLOW_ALLOW_WRITE (Set to 'true' to enable trigger-dag and clear-task tools. Default read-only.), AIRFLOW_TOOLS (Comma-separated category allowlist (airflow,meta).), AIRFLOW_DISABLE (Comma-separated category disablelist.).
The author declared them in the registry entry; get the values from the project itself.
Observe and operate Hatchet workflows from an AI agent — runs, logs, trigger, cancel, replay.
A committed markdown dev log and task graph that agents read and write over MCP.
CircleCI's MCP server: inspect projects, runs, workflows, jobs, logs, tests, and artifacts.
Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.
SigNoz MCP server: access metrics, traces, logs, alerts, and dashboards via AI assistants
Diagnose Airflow failures from UI links with bounded logs and optional recovery actions.
Read time entries, projects, clients, tasks and invoices; log and update tracked time.
Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens.
Answers built from our own checks of this server.