MCP Tabular Data Analysis Server

Instructions

Generate comprehensive statistics for a tabular dataset.

Args:
    file_path: Path to CSV or SQLite file
    include_all: If True, include statistics for all columns (not just numeric)

Returns:
    Dictionary containing:
    - shape: (rows, columns)
    - columns: List of column names with their types
    - numeric_stats: Descriptive statistics for numeric columns
    - missing_values: Count of missing values per column
    - sample: First 5 rows as preview

Implementation Reference

• src/mcp_tabular/server.py:108-160 (handler)

  Main handler function for the 'describe_dataset' tool. Loads dataset from CSV/SQLite, computes comprehensive statistics including shape, column types, missing values, numeric descriptive stats (with skew/kurtosis), categorical summaries, and a data sample.

  @mcp.tool()
  def describe_dataset(file_path: str, include_all: bool = False) -> dict[str, Any]:
      """
      Generate comprehensive statistics for a tabular dataset.
      
      Args:
          file_path: Path to CSV or SQLite file
          include_all: If True, include statistics for all columns (not just numeric)
      
      Returns:
          Dictionary containing:
          - shape: (rows, columns)
          - columns: List of column names with their types
          - numeric_stats: Descriptive statistics for numeric columns
          - missing_values: Count of missing values per column
          - sample: First 5 rows as preview
      """
      df = _load_data(file_path)
      
      # Basic info
      result = {
          "shape": {"rows": len(df), "columns": len(df.columns)},
          "columns": {
              col: str(df[col].dtype) for col in df.columns
          },
          "missing_values": df.isnull().sum().to_dict(),
      }
      
      # Numeric statistics
      numeric_cols = _get_numeric_columns(df)
      if numeric_cols:
          stats_df = df[numeric_cols].describe()
          # Add additional stats
          stats_df.loc["median"] = df[numeric_cols].median()
          stats_df.loc["skew"] = df[numeric_cols].skew()
          stats_df.loc["kurtosis"] = df[numeric_cols].kurtosis()
          result["numeric_stats"] = stats_df.to_dict()
      
      # Categorical columns info
      cat_cols = df.select_dtypes(include=["object", "category"]).columns.tolist()
      if cat_cols:
          result["categorical_columns"] = {
              col: {
                  "unique_values": df[col].nunique(),
                  "top_values": df[col].value_counts().head(5).to_dict()
              }
              for col in cat_cols
          }
      
      # Sample data
      result["sample"] = df.head(5).to_dict(orient="records")
      
      return result

• src/mcp_tabular/server.py:103-106 (helper)

  Helper function to identify numeric columns, used in describe_dataset for statistics computation.

  def _get_numeric_columns(df: pd.DataFrame) -> list[str]:
      """Get list of numeric column names."""
      return df.select_dtypes(include=[np.number]).columns.tolist()

• src/mcp_tabular/server.py:70-101 (helper)

  Core helper function to load datasets from CSV or SQLite files, handling path resolution and table selection for databases. Called by describe_dataset.

  def _load_data(file_path: str) -> pd.DataFrame:
      """Load data from CSV or SQLite file."""
      path = _resolve_path(file_path)
      
      if not path.exists():
          raise FileNotFoundError(
              f"File not found: {file_path}\n"
              f"Resolved to: {path}\n"
              f"Project root: {_PROJECT_ROOT}\n"
              f"Current working directory: {Path.cwd()}"
          )
      
      suffix = path.suffix.lower()
      
      if suffix == ".csv":
          return pd.read_csv(str(path))
      elif suffix in (".db", ".sqlite", ".sqlite3"):
          # For SQLite, list tables or load first table
          conn = sqlite3.connect(str(path))
          tables = pd.read_sql_query(
              "SELECT name FROM sqlite_master WHERE type='table'", conn
          )
          if tables.empty:
              conn.close()
              raise ValueError(f"No tables found in SQLite database: {file_path}")
          first_table = tables.iloc[0]["name"]
          df = pd.read_sql_query(f"SELECT * FROM {first_table}", conn)
          conn.close()
          return df
      else:
          raise ValueError(f"Unsupported file format: {suffix}. Use .csv or .db/.sqlite")

• src/mcp_tabular/server.py:49-68 (helper)

  Helper to resolve relative file paths to absolute paths based on project root, used by _load_data.

  def _resolve_path(file_path: str) -> Path:
      """
      Resolve file path relative to project root if it's a relative path.
      
      Args:
          file_path: Absolute or relative file path
      
      Returns:
          Resolved absolute Path
      """
      path = Path(file_path)
      
      # If absolute path, use as-is
      if path.is_absolute():
          return path
      
      # Otherwise, resolve relative to project root
      resolved = _PROJECT_ROOT / path
      return resolved.resolve()

• src/mcp_tabular/server.py:108-108 (registration)

  MCP tool registration decorator for the describe_dataset function.

  @mcp.tool()