MCP Tabular Data Analysis Server

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

Detect anomalies/outliers in a numeric column. Args: file_path: Path to CSV or SQLite file column: Name of the numeric column to analyze method: Detection method - 'zscore' (default), 'iqr', or 'isolation_forest' threshold: Threshold for anomaly detection (default 3.0 for zscore, 1.5 for IQR) Returns: Dictionary containing: - method: Detection method used - anomaly_count: Number of anomalies found - anomaly_indices: Row indices of anomalies - anomalies: The anomalous rows - statistics: Column statistics

Compute correlation matrix between numeric columns. Args: file_path: Path to CSV or SQLite file columns: List of columns to include (default: all numeric columns) method: Correlation method - 'pearson' (default), 'spearman', or 'kendall' Returns: Dictionary containing: - method: Correlation method used - correlation_matrix: Full correlation matrix - top_correlations: Top 10 strongest correlations (excluding self-correlations)

Filter rows based on a condition. Args: file_path: Path to CSV or SQLite file column: Column name to filter on operator: Comparison operator - 'eq', 'ne', 'gt', 'gte', 'lt', 'lte', 'contains', 'startswith', 'endswith' value: Value to compare against limit: Maximum number of rows to return (default 100) Returns: Dictionary containing: - filter_applied: Description of the filter - original_count: Number of rows before filtering - filtered_count: Number of rows after filtering - rows: Filtered rows (up to limit)

Execute a SQL query on a SQLite database. Args: db_path: Path to SQLite database file query: SQL query to execute (SELECT queries only for safety) limit: Maximum number of rows to return (default 100) Returns: Dictionary containing: - query: The executed query - row_count: Number of rows returned - columns: List of column names - rows: Query results

List all tables in a SQLite database. Args: db_path: Path to SQLite database file Returns: Dictionary containing table names and their schemas

Group data and compute aggregations. Args: file_path: Path to CSV or SQLite file group_by: Columns to group by aggregations: Dictionary mapping column names to list of aggregation functions (e.g., {"sales": ["sum", "mean"], "quantity": ["count", "max"]}) Supported: sum, mean, median, min, max, count, std, var Returns: Dictionary containing grouped and aggregated data

List available data files in the project data directory. Args: data_dir: Relative path to data directory (default: "data") Returns: Dictionary containing list of available CSV and SQLite files

Create a pivot table from tabular data - the most common business analysis operation. Args: file_path: Path to CSV or SQLite file index: Column(s) to use as row labels (grouping) columns: Column(s) to use as column headers (optional) values: Column to aggregate (default: first numeric column) aggfunc: Aggregation function - 'sum', 'mean', 'count', 'min', 'max', 'median', 'std' fill_value: Value to replace missing entries (default: None = show as null) Returns: Dictionary containing the pivot table data and metadata Example: create_pivot_table( file_path="data/sales.csv", index=["region"], columns=["category"], values="revenue", aggfunc="sum" )

Generate a comprehensive data quality assessment report. Essential for understanding data health before analysis. Args: file_path: Path to CSV or SQLite file Returns: Dictionary containing: - completeness: Missing value analysis per column - uniqueness: Duplicate detection - validity: Data type consistency and outlier counts - overall_score: Data quality score (0-100)

Perform time series analysis including trend detection, seasonality, and statistics. Args: file_path: Path to CSV or SQLite file date_column: Name of the date/datetime column value_column: Name of the numeric column to analyze freq: Frequency for resampling - 'D' (daily), 'W' (weekly), 'M' (monthly), 'Q' (quarterly), 'Y' (yearly) include_forecast: If True, include simple moving average forecast Returns: Dictionary containing: - trend: Overall trend direction and statistics - statistics: Time series statistics - moving_averages: 7, 30, 90 period moving averages - seasonality: Day of week / month patterns - forecast: Simple forecast if requested

Generate a chart/visualization from tabular data. Returns chart as base64-encoded PNG for display. Args: file_path: Path to CSV or SQLite file chart_type: Type of chart - 'bar', 'line', 'scatter', 'histogram', 'pie', 'box' x_column: Column for X-axis (not needed for histogram/pie) y_column: Column for Y-axis values group_by: Optional column for grouping/coloring title: Chart title (auto-generated if not provided) output_format: 'base64' (default) or 'file' (saves to data/charts/) Returns: Dictionary containing chart data as base64 or file path

Merge/join two datasets together - essential for combining data sources. Args: file_path_left: Path to left/primary dataset file_path_right: Path to right/secondary dataset on: Column(s) to join on (if same name in both datasets) left_on: Column name in left dataset to join on right_on: Column name in right dataset to join on how: Join type - 'inner', 'left', 'right', 'outer' preview_limit: Number of rows to return in preview Returns: Dictionary containing merged data preview and statistics

Perform statistical hypothesis tests on data. Args: file_path: Path to CSV or SQLite file test_type: Type of test: - 'ttest_ind': Independent samples t-test (compare 2 groups) - 'ttest_paired': Paired samples t-test - 'chi_squared': Chi-squared test for categorical independence - 'anova': One-way ANOVA (compare 3+ groups) - 'mann_whitney': Non-parametric alternative to t-test - 'pearson': Pearson correlation test - 'spearman': Spearman correlation test column1: First column for analysis column2: Second column (required for correlation, optional for t-test) group_column: Column defining groups (for t-test, ANOVA) alpha: Significance level (default 0.05) Returns: Dictionary containing test statistic, p-value, and interpretation

Automatically generate interesting insights about a dataset. Perfect for quick data exploration and understanding. Args: file_path: Path to CSV or SQLite file max_insights: Maximum number of insights to generate (default 10) Returns: Dictionary containing automatically discovered insights

Export filtered/transformed data to a new CSV file. Args: file_path: Path to source CSV or SQLite file output_name: Name for output file (without extension, saved to data/ folder) filter_column: Optional column to filter on filter_operator: Filter operator - 'eq', 'ne', 'gt', 'gte', 'lt', 'lte', 'contains' filter_value: Value to filter by columns: List of columns to include (default: all) sort_by: Column to sort by sort_ascending: Sort direction (default: ascending) limit: Maximum rows to export Returns: Dictionary containing export details and file path