Apache Airflow
MCP server implementation by call518 that provides AI assistants with complete access to Apache Airflow cluster management and monitoring through REST API integration, built using Python with FastMCP and aiohttp for high-performance async operations. The implementation offers 43 tools covering DAG management (listing, triggering, pausing), cluster health monitoring, pool and variable management, task instance tracking with comprehensive filtering, XCom data access, configuration management, and detailed analytics including event logs, import errors, and performance metrics. Built with modern async HTTP architecture featuring connection pooling, persistent sessions, and optimized pagination defaults, it serves DevOps teams managing Airflow workflows, data engineers monitoring pipeline health, and organizations requiring conversational access to Airflow operations without direct UI interaction, with support for both stdio and HTTP transport methods plus Docker deployment options.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/call518/mcp-airflow-api
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Apache Airflow from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.