List Available Lookups

Instructions

Implementation Reference

• mcp_server/server.py:451-467 (handler)

  Main handler function for the 'detection_list_lookups' tool. It reads all CSV files from LOOKUPS_DIR, returning a list with each file's name, row count, and column headers.

  def detection_list_lookups() -> dict[str, Any]:
      """List all available lookup files and their metadata (row counts, columns).
  
      Use this tool to discover what datasets are available before querying.
      """
      lookups = []
      for csv_file in sorted(LOOKUPS_DIR.glob("*.csv")):
          with open(csv_file, "r", encoding="utf-8") as f:
              reader = csv.DictReader(f)
              rows = list(reader)
              lookups.append({
                  "filename": csv_file.name,
                  "rows": len(rows),
                  "columns": reader.fieldnames or [],
              })
  
      return {"count": len(lookups), "lookups": lookups}

• mcp_server/server.py:442-450 (registration)

  Registration of the 'detection_list_lookups' function as an MCP tool via the @mcp.tool() decorator with annotations including title 'List Available Lookups', readOnlyHint=True, destructiveHint=False, idempotentHint=True, openWorldHint=False.

  @mcp.tool(
      annotations={
          "title": "List Available Lookups",
          "readOnlyHint": True,
          "destructiveHint": False,
          "idempotentHint": True,
          "openWorldHint": False,
      },
  )

• mcp_server/server.py:451-467 (schema)

  The return type is dict[str, Any] with the schema: {'count': int, 'lookups': list[{'filename': str, 'rows': int, 'columns': list[str]}]}. No input parameters. No explicit pydantic model, inferred from the function return logic.

  def detection_list_lookups() -> dict[str, Any]:
      """List all available lookup files and their metadata (row counts, columns).
  
      Use this tool to discover what datasets are available before querying.
      """
      lookups = []
      for csv_file in sorted(LOOKUPS_DIR.glob("*.csv")):
          with open(csv_file, "r", encoding="utf-8") as f:
              reader = csv.DictReader(f)
              rows = list(reader)
              lookups.append({
                  "filename": csv_file.name,
                  "rows": len(rows),
                  "columns": reader.fieldnames or [],
              })
  
      return {"count": len(lookups), "lookups": lookups}

• mcp_server/server.py:34-40 (helper)

  Helper function _load_csv used by the tool handler to load CSV files from the LOOKUPS_DIR directory.

  def _load_csv(filename: str) -> list[dict[str, str]]:
      """Load a CSV lookup file and return rows as list of dicts."""
      filepath = LOOKUPS_DIR / filename
      if not filepath.exists():
          return []
      with open(filepath, "r", encoding="utf-8") as f:
          return list(csv.DictReader(f))

• mcp_server/server.py:18-18 (helper)

  LOOKUPS_DIR path definition used by the tool to find CSV files.

  LOOKUPS_DIR = Path(__file__).parent.parent / "lookups"