get_prompt_template
Retrieve structured prompt templates for LLM interactions with Airflow operations, enabling optimal guidance for DAG inspection, task monitoring, and cluster management.
Instructions
[Tool Role]: Provides comprehensive prompt template for LLM interactions with Airflow operations.
Args: section: Optional section name to get specific part of template mode: Optional mode (summary/detailed) to control response verbosity
Returns: Comprehensive template or specific section for optimal LLM guidance
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| section | No | ||
| mode | No |
Implementation Reference
- Handler function implementing the 'get_prompt_template' MCP tool. Loads the prompt template from file and returns full content or extracts specific sections by matching content.
@mcp.tool() async def get_prompt_template(section: Optional[str] = None, mode: Optional[str] = None) -> str: """ [Tool Role]: Provides comprehensive prompt template for LLM interactions with Airflow operations. Args: section: Optional section name to get specific part of template mode: Optional mode (summary/detailed) to control response verbosity Returns: Comprehensive template or specific section for optimal LLM guidance """ template = read_prompt_template(PROMPT_TEMPLATE_PATH) if section: sections = parse_prompt_sections(template) for i, s in enumerate(sections): if section.lower() in s.lower(): return sections[i + 1] # +1 to skip the title section return f"Section '{section}' not found." return template - Utility function to read the prompt template Markdown file from disk.
def read_prompt_template(path: str) -> str: """ Reads the MCP prompt template file and returns its content as a string. """ with open(path, "r", encoding="utf-8") as f: return f.read() - Utility function to parse the prompt template string into list of headings and corresponding section contents.
def parse_prompt_sections(template: str): """ Parses the prompt template into section headings and sections. Returns (headings, sections). """ lines = template.splitlines() sections = [] current = [] headings = [] for line in lines: if line.startswith("## "): if current: sections.append("\n".join(current)) current = [] headings.append(line[3:].strip()) current.append(line) else: current.append(line) if current: sections.append("\n".join(current)) return headings, sections - src/mcp_airflow_api/tools/v1_tools.py:13-28 (registration)Registration function for v1 API tools. Sets v1-specific airflow_request and calls register_common_tools(mcp), which defines and registers the get_prompt_template tool.
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)") - src/mcp_airflow_api/tools/v2_tools.py:14-104 (registration)Registration function for v2 API tools. Sets v2-specific airflow_request and calls register_common_tools(mcp), which defines and registers the get_prompt_template tool.
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) # Add V2-exclusive tools (2 tools) @mcp.tool() async def list_assets(limit: int = 20, offset: int = 0, uri_pattern: Optional[str] = None) -> Dict[str, Any]: """ [V2 New] List all assets in the system for data-aware scheduling. Assets are a key feature in Airflow 3.0 for data-aware scheduling. They enable workflows to be triggered by data changes rather than time schedules. Args: limit: Maximum number of assets to return (default: 20) offset: Number of assets to skip for pagination (default: 0) uri_pattern: Filter assets by URI pattern (optional) Returns: Dict containing assets list, pagination info, and metadata """ params = {'limit': limit, 'offset': offset} if uri_pattern: params['uri_pattern'] = uri_pattern query_string = "&".join([f"{k}={v}" for k, v in params.items()]) resp = await airflow_request_v2("GET", f"/assets?{query_string}") resp.raise_for_status() data = resp.json() return { "assets": data.get("assets", []), "total_entries": data.get("total_entries", 0), "limit": limit, "offset": offset, "api_version": "v2", "feature": "assets" } @mcp.tool() async def list_asset_events(limit: int = 20, offset: int = 0, asset_uri: Optional[str] = None, source_dag_id: Optional[str] = None) -> Dict[str, Any]: """ [V2 New] List asset events for data lineage tracking. Asset events track when assets are created or updated by DAGs. This enables data lineage tracking and data-aware scheduling in Airflow 3.0. Args: limit: Maximum number of events to return (default: 20) offset: Number of events to skip for pagination (default: 0) asset_uri: Filter events by specific asset URI (optional) source_dag_id: Filter events by source DAG that produced the event (optional) Returns: Dict containing asset events list, pagination info, and metadata """ params = {'limit': limit, 'offset': offset} if asset_uri: params['asset_uri'] = asset_uri if source_dag_id: params['source_dag_id'] = source_dag_id query_string = "&".join([f"{k}={v}" for k, v in params.items()]) resp = await airflow_request_v2("GET", f"/assets/events?{query_string}") resp.raise_for_status() data = resp.json() return { "asset_events": data.get("asset_events", []), "total_entries": data.get("total_entries", 0), "limit": limit, "offset": offset, "api_version": "v2", "feature": "asset_events" } logger.info("Registered all Airflow API v2 tools (43 common + 2 assets + 4 management = 49 tools)")