Skip to main content
Glama

running_dags

Monitor active DAG runs in Apache Airflow clusters to track workflow execution status and identify currently processing pipelines.

Instructions

[Tool Role]: Lists all currently running DAG runs in the Airflow cluster.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Core handler implementation for the 'running_dags' tool. Fetches running DAG runs from Airflow API endpoint '/dags/~/dagRuns?state=running', processes the response, and returns structured data including run details and summary statistics.
    @mcp.tool()
    async def running_dags() -> Dict[str, Any]:
        """[Tool Role]: Lists all currently running DAG runs in the Airflow cluster."""
        resp = await airflow_request("GET", "/dags/~/dagRuns?state=running&limit=1000&order_by=-start_date")
        resp.raise_for_status()
        data = resp.json()
    
        running_runs = []
        for run in data.get("dag_runs", []):
            run_info = {
                "dag_id": run.get("dag_id"),
                "dag_display_name": run.get("dag_display_name"),
                "run_id": run.get("run_id"),
                "run_type": run.get("run_type"),
                "state": run.get("state"),
                "execution_date": run.get("execution_date"),
                "start_date": run.get("start_date"),
                "end_date": run.get("end_date"),
                "data_interval_start": run.get("data_interval_start"),
                "data_interval_end": run.get("data_interval_end"),
                "external_trigger": run.get("external_trigger"),
                "conf": run.get("conf"),
                "note": run.get("note")
            }
            running_runs.append(run_info)
    
        return {
            "dag_runs": running_runs,
            "total_running": len(running_runs),
            "query_info": {
                "state_filter": "running",
                "limit": 1000,
                "order_by": "start_date (descending)"
            }
        }
  • Registration entry point for v1 API version. Sets the v1-specific airflow_request function and calls register_common_tools(mcp), which defines and registers the running_dags handler.
    def register_tools(mcp):
        """Register v1 tools by importing common tools with v1 request function."""
        
        logger.info("Initializing MCP server for Airflow API v1")
        logger.info("Loading Airflow API v1 tools (Airflow 2.x)")
        
        # Set the global request function to v1
        common_tools.airflow_request = airflow_request_v1
        
        # Register all 56 common tools (includes management tools)
        common_tools.register_common_tools(mcp)
        
        # V1 has no exclusive tools - all tools are shared with v2
        
        logger.info("Registered all Airflow API v1 tools (56 tools: 43 core + 13 management tools)")
  • Registration entry point for v2 API version. Sets the v2-specific airflow_request function and calls register_common_tools(mcp), which defines and registers the running_dags handler.
    def register_tools(mcp):
        """Register v2 tools: common tools + v2-exclusive asset tools."""
        
        logger.info("Initializing MCP server for Airflow API v2")
        logger.info("Loading Airflow API v2 tools (Airflow 3.0+)")
        
        # Set the global request function to v2
        common_tools.airflow_request = airflow_request_v2
        
        # Register all 43 common tools
        common_tools.register_common_tools(mcp)
  • The register_common_tools function where all common tools, including running_dags, are defined and registered using @mcp.tool() decorator when this function is called from v1/v2_tools.
    def register_common_tools(mcp):
        """Register all 43 common tools that work with both v1 and v2 APIs."""
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states the tool's function without disclosing behavioral traits like pagination, rate limits, permissions required, or output format details. It fails to address how 'currently running' is defined (e.g., real-time vs cached) or error handling, leaving significant gaps for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the core functionality ('Lists all currently running DAG runs') and specifies the context ('in the Airflow cluster'). There is no wasted verbiage, making it highly efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which handles return values) and no parameters, the description's focus on purpose is adequate. However, with no annotations and a read operation that may involve complex runtime data, it lacks completeness in behavioral aspects like data freshness or cluster-specific constraints, leaving room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description appropriately omits parameter details, maintaining focus on the tool's purpose without redundancy. A baseline of 4 is applied as it efficiently handles the lack of parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Lists') and resource ('all currently running DAG runs in the Airflow cluster'), distinguishing it from sibling tools like 'list_dags' (which lists DAGs generally) or 'failed_dags' (which lists failed runs). It precisely defines scope without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when needing to monitor active DAG executions, but provides no explicit guidance on when to use this tool versus alternatives like 'list_task_instances_all' or 'dag_run_duration'. It lacks clear exclusions or prerequisites, leaving context interpretation to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/call518/MCP-Airflow-API'

If you have feedback or need assistance with the MCP directory API, please join our Discord server