get_table_schema

Instructions

Implementation Reference

• src/adx_mcp_server/server.py:243-262 (handler)

  The main handler function for the get_table_schema tool. Retrieves schema information for a specified ADX table by executing '{table_name} | getschema' query. Uses validate_table_name for injection protection, get_kusto_client for connection, and format_query_results for output formatting.

  @mcp.tool(description="Retrieves the schema information for a specified table in the Azure Data Explorer database, including column names, data types, and other schema-related metadata.")
  async def get_table_schema(table_name: str) -> List[Dict[str, Any]]:
      """Get schema information for a specific table."""
      table_name = validate_table_name(table_name)
      logger.info("Getting table schema", table_name=table_name, database=config.database)
  
      if not config.cluster_url or not config.database:
          logger.error("Missing ADX configuration")
          raise ValueError("Azure Data Explorer configuration is missing. Please set ADX_CLUSTER_URL and ADX_DATABASE environment variables.")
  
      try:
          client = get_kusto_client()
          query = f"{table_name} | getschema"
          result_set = client.execute(config.database, query)
          results = format_query_results(result_set)
          logger.info("Schema retrieved successfully", table_name=table_name, column_count=len(results))
          return results
      except Exception as e:
          logger.error("Failed to get table schema", table_name=table_name, error=str(e), exception_type=type(e).__name__)
          raise

• src/adx_mcp_server/server.py:243-243 (registration)

  The tool is registered via the @mcp.tool decorator from FastMCP, which makes it available as an MCP tool with the given description.

  @mcp.tool(description="Retrieves the schema information for a specified table in the Azure Data Explorer database, including column names, data types, and other schema-related metadata.")

• src/adx_mcp_server/server.py:176-191 (helper)

  Helper function that validates table names against a regex pattern to prevent KQL injection attacks. Called at line 246 before executing the schema query.

  def validate_table_name(table_name: str) -> str:
      """Validate a KQL table name to prevent injection attacks.
  
      Allows simple identifiers (my_table) and dot-qualified names (database.table).
      Rejects any characters that could enable KQL injection.
      """
      if not table_name or not table_name.strip():
          raise ValueError("Table name cannot be empty")
      table_name = table_name.strip()
      if not _TABLE_NAME_PATTERN.match(table_name):
          raise ValueError(
              f"Invalid table name: '{table_name}'. "
              "Table names must contain only letters, digits, underscores, "
              "and dots (for qualified names like 'database.table')."
          )
      return table_name

• src/adx_mcp_server/server.py:84-137 (helper)

  Helper that creates and configures an Azure Kusto client with appropriate credentials (WorkloadIdentity or DefaultAzureCredential). Used at line 254 to execute the schema query.

  def get_kusto_client() -> KustoClient:
      """
      Create and configure a Kusto client with appropriate Azure credentials.
  
      Prioritizes WorkloadIdentityCredential when running in AKS with workload identity,
      falls back to DefaultAzureCredential for other authentication methods.
  
      Returns:
          KustoClient: Configured Kusto client instance
      """
      tenant_id = os.environ.get('AZURE_TENANT_ID')
      client_id = os.environ.get('AZURE_CLIENT_ID')
      token_file_path = os.environ.get('ADX_TOKEN_FILE_PATH', '/var/run/secrets/azure/tokens/azure-identity-token')
  
      if tenant_id and client_id:
          logger.info(
              "Using WorkloadIdentityCredential",
              client_id=client_id,
              tenant_id=tenant_id,
              token_file_path=token_file_path
          )
          try:
              credential = WorkloadIdentityCredential(
                  tenant_id=tenant_id,
                  client_id=client_id,
                  token_file_path=token_file_path
              )
          except Exception as e:
              logger.warning(
                  "Failed to initialize WorkloadIdentityCredential, falling back",
                  error=str(e),
                  exception_type=type(e).__name__
              )
              credential = DefaultAzureCredential()
      else:
          logger.info("Using DefaultAzureCredential (missing WorkloadIdentity credentials)")
          credential = DefaultAzureCredential()
  
      try:
          kcsb = KustoConnectionStringBuilder.with_azure_token_credential(
              connection_string=config.cluster_url,
              credential=credential
          )
          client = KustoClient(kcsb)
          logger.debug("Kusto client initialized successfully", cluster_url=config.cluster_url)
          return client
      except Exception as e:
          logger.error(
              "Failed to create Kusto client",
              error=str(e),
              exception_type=type(e).__name__,
              cluster_url=config.cluster_url
          )
          raise

• src/adx_mcp_server/server.py:139-172 (helper)

  Helper that formats raw Kusto query results into a list of dictionaries with column names as keys. Used at line 257 to process the schema results.

  def format_query_results(result_set) -> List[Dict[str, Any]]:
      """
      Format Kusto query results into a list of dictionaries.
  
      Args:
          result_set: Raw result set from KustoClient
  
      Returns:
          List of dictionaries with column names as keys
      """
      if not result_set or not result_set.primary_results:
          logger.debug("Empty or null result set received")
          return []
  
      try:
          primary_result = result_set.primary_results[0]
          columns = [col.column_name for col in primary_result.columns]
  
          formatted_results = []
          for row in primary_result.rows:
              record = {}
              for i, value in enumerate(row):
                  record[columns[i]] = value
              formatted_results.append(record)
  
          logger.debug("Query results formatted", row_count=len(formatted_results), columns=columns)
          return formatted_results
      except Exception as e:
          logger.error(
              "Error formatting query results",
              error=str(e),
              exception_type=type(e).__name__
          )
          raise