data_mean
Calculate mean values for each column in a dataset using the input data file path. Simplify data analysis and preprocessing within the MCP Data Wrangler server for accurate descriptive statistics.
Instructions
Mean values for each column
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input_data_file_path | No | Path to the input data file |
Implementation Reference
- The handler function that implements the core logic of the 'data_mean' tool: loads data from file, computes column means using Polars DataFrame.mean(), formats as JSON, and returns as TextContent.
async def handle_data_mean( arguments: dict[str, Any], ) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]: data_mean_input = DataMeanInputSchema.from_args(arguments) mean_df = data_mean_input.df.mean() # Convert the DataFrame to a dictionary format mean_dict = { "description": "Mean values for each column", "mean_values": { col: str(val) if val is not None else None for col, val in zip(mean_df.columns, mean_df.row(0)) }, } return [ types.TextContent( type="text", text=json.dumps(mean_dict), ) ] - Pydantic model subclassing Data for input validation of 'data_mean' tool. Provides inputSchema() for MCP Tool registration, and factory methods to load DataFrame from file path argument.
class DataMeanInputSchema(Data): model_config = ConfigDict( validate_assignment=True, frozen=True, extra="forbid", arbitrary_types_allowed=True, ) @staticmethod def input_schema() -> dict: return { "type": "object", "properties": { "input_data_file_path": { "type": "string", "description": "Path to the input data file", }, }, } @staticmethod def from_schema(input_data_file_path: str) -> "DataMeanInputSchema": data = Data.from_file(input_data_file_path) return DataMeanInputSchema(df=data.df) @staticmethod def from_args(arguments: dict[str, Any]) -> "DataMeanInputSchema": input_data_file_path = arguments["input_data_file_path"] return DataMeanInputSchema.from_schema(input_data_file_path=input_data_file_path) - src/mcp_server_data_wrangler/tools/tools.py:112-116 (registration)MCP Tool registration for 'data_mean': specifies name 'data_mean', description 'Mean values for each column', and references input schema from DataMeanInputSchema.input_schema().
types.Tool( name=MCPServerDataWrangler.data_mean.value[0], description=MCPServerDataWrangler.data_mean.value[1], inputSchema=DataMeanInputSchema.input_schema(), ), - src/mcp_server_data_wrangler/tools/tools.py:161-162 (registration)Handler mapping registration: associates tool name 'data_mean' with handle_data_mean function.
MCPServerDataWrangler.data_mean.value[0]: handle_data_mean, MCPServerDataWrangler.data_mean_horizontal.value[0]: handle_data_mean_horizontal, - Enum definition providing the canonical name and description for the 'data_mean' tool.
data_mean = ("data_mean", "Mean values for each column")