# Airflow DAG Doctor

> Airflow DAG Doctor is an MCP server for developer tools. Diagnose exported Airflow 3.2 and 3.3 DAG source and task incidents with cited evidence. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Platforms:** API, CLI
- **Website:** https://mcp.contentsweep.ai/dag-doctor
- **MCP Registry name:** ai.contentsweep/airflow-dag-doctor
- **Categories:** developer tools, analytics and data
- **Listing updated:** 2026-11-14

## About

Airflow DAG Doctor works from exported material rather than a live deployment. You upload DAG source and context about a failed task, and it returns a diagnosis tied to specific evidence, with missing context and uncertainty stated openly. It does not connect to Airflow or apply changes, and uploaded code is parsed without being imported or run.

For incidents it looks for dependency failures, deadlines, upstream failures, pool exhaustion, XCom issues and executor mismatches. For review it runs static checks on parse-time work, branch joins, sensor settings and retry side effects, and flags unresolved dynamic code for a person to check. Support covers exported Airflow 3.2 and 3.3 evidence.

Local tools are free. Hosted use is prepaid at $20 for 20 reports, with five trials per verified organization and no subscription. A report is charged only for a completed supported diagnosis, and retries, unsupported inputs and platform failures are free.

## Features

- **Incident diagnosis:** Finds likely causes such as pool exhaustion, XCom problems and executor mismatch.
- **Static DAG review:** Checks parse-time work, branch joins, sensors and retry side effects.
- **Evidence-linked findings:** Ties each finding to the supplied evidence and states coverage gaps.
- **No code execution:** Uploaded source is parsed without imports or execution.
- **Free local tools:** Local use is free; hosted reports are prepaid.
- **Repeatable demos:** Owned synthetic scenarios can be reproduced.

## Good for

- Work out why an exported Airflow task failed
- Review a DAG for parse-time work before deploying
- Check retry behaviour for unsafe side effects
- Find executor mismatches between DAG and setup

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http airflow-dag-doctor https://mcp.contentsweep.ai/v1/dag-doctor/mcp/
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.contentsweep.ai/v1/dag-doctor/mcp/
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "airflow-dag-doctor": {
      "url": "https://mcp.contentsweep.ai/v1/dag-doctor/mcp/"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "airflow-dag-doctor": {
      "type": "http",
      "url": "https://mcp.contentsweep.ai/v1/dag-doctor/mcp/"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "airflow-dag-doctor": {
      "serverUrl": "https://mcp.contentsweep.ai/v1/dag-doctor/mcp/"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "airflow-dag-doctor": {
      "type": "http",
      "url": "https://mcp.contentsweep.ai/v1/dag-doctor/mcp/"
    }
  }
}
```

## FAQ

### Does it connect to my Airflow?

No. It works on exported evidence and applies no changes.

### Which versions are supported?

Exported Airflow 3.2 and 3.3 evidence.

### What does a hosted report cost?

$20 buys 20 reports, and five trials are given per verified organization.

### When is a report free?

Missing context, unsupported inputs, platform failures and retries of the same job are free.

### Is Airflow DAG Doctor free?

Airflow DAG Doctor is a paid product with a free trial.

### How do I add Airflow DAG Doctor to Claude Code?

Run this command in your terminal: claude mcp add --transport http airflow-dag-doctor https://mcp.contentsweep.ai/v1/dag-doctor/mcp/

### What are the best alternatives to Airflow DAG Doctor?

The closest alternatives to Airflow DAG Doctor are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/airflow-dag-doctor
