DAG Doctor integration
Connect to https://mcp.contentsweep.ai/v1/dag-doctor/mcp/ with a verified organization's X-API-Key. Follow upload → preview → quote → start → poll → report. Keep the original quote/idempotency key on retries. Local stdio diagnose_airflow_dag is available through the standalone dagdoctor-mcp executable.
The hosted tool never accepts server paths. Upload actual relative Python source files and exported incident context. Use examples/executor-mismatch/bundle.json for an owned synthetic upload.
The adjacent server manifest is prepared release metadata. Availability, public Registry acceptance, sandbox payment qualification, live purchasing and independent adoption are separate facts; consult the product release receipt before claiming them.
Free local tools
Python 3.12+ is required. Download the wheel, verify it against the SHA256 manifest, then install into a separate environment:
python3.12 -m venv .venv-dag-doctor
.venv-dag-doctor/bin/python -m pip install './contentsweep_dag_doctor-1.0.0-py3-none-any.whl[mcp]'
.venv-dag-doctor/bin/dagdoctor diagnose examples/pool-wait/source --runtime-context examples/pool-wait/incident.json --format json
The example paths above refer to the prepared distribution bundle. Local MCP command: .venv-dag-doctor/bin/dagdoctor-mcp; tool: diagnose_airflow_dag. This local-only wheel has no hosted billing code. Local findings may produce exit 2, missing context exit 3, invalid input exit 5.
Examples and distribution
The checked-in examples/ contain owned synthetic inputs and qualified reference reports. Install the maintained skill using the public-source instructions below. The engine and MCP connection are separate setup steps. server.json describes the hosted MCP interface; catalog acceptance and client qualification are tracked separately. Internal qualification does not establish customer adoption.
Install the agent skill
Install this skill in the intended project, then choose the coding agents you use:
npx skills add founder-sweep/contentsweep-dag-doctor --skill diagnose-airflow-exports
For Claude Code, add the ContentSweep marketplace and install this product:
claude plugin marketplace add founder-sweep/contentsweep-supplier-feed-examples
claude plugin install contentsweep-dag-doctor@contentsweep
The marketplace contains Supplier Feeds, Data Quality Gate, Inspector, Schema Mapper, DAG Doctor and Deployment Fixer. Each plugin loads its existing product skill and companion references. Installation grants no upload, spending, business-rule approval or destination-write permission. MCP connections and runtime dependencies are configured separately using the bundled agent setup. Review the supported scope, privacy, free/local options and current hosted pricing before use.
Gemini, Kilo, Cline and Cursor
Diagnose exported Airflow 3.2/3.3 incidents with evidence and explicit coverage gaps.
Follow client installation and recovery. Native configuration examples, required settings, the existing skill and supported scope are included. Catalog submission and acceptance are recorded separately.
