Airflow
Airflow MCP Server provides a bridge between Claude and Apache Airflow, enabling direct interaction with Airflow workflows through the API. Built by Abhishek Bhakat, it supports both read-only (safe) and full-access (unsafe) operation modes, allowing users to list DAGs, check statuses, trigger runs, and manage Airflow resources without leaving their conversation interface. The implementation parses the Airflow OpenAPI specification to dynamically generate tools, supports both token and cookie-based authentication, and handles parameter validation - making it particularly valuable for DevOps teams who need to monitor and control workflow orchestration through natural language.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/abhishekbhakat/airflow-mcp-server
- Author type
- human
- Updated
- 2026-08-31
Use via MCP
Resolve 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.