arrow-cache-mcp

# Arrow Cache MCP A powerful data science toolkit and MCP server leveraging Apache Arrow for efficient memory management and data processing. ## Features - **High Performance Data Handling**: Efficient memory management using Apache Arrow - **Intelligent Memory Management**: Automatic partitioning and compression of large datasets - **Multiple File Format Support**: Load datasets from CSV, Parquet, Arrow, Feather, JSON, Excel, and more - **SQL Query Capabilities**: Advanced SQL analytics with DuckDB integration - **Visualization Support**: Create plots and charts from your datasets - **AI-Powered Data Analysis**: Optional Claude integration for natural language queries - **Memory Overflow Protection**: Automatic spilling to disk when memory limits are reached ## Components ### Resources The server exposes cached datasets as resources: - Custom `arrowcache://` URI scheme for accessing datasets - Each dataset resource has detailed metadata about size, shape, and structure ### Tools The server implements the following tools: - **run_sql_query**: Execute SQL queries against cached datasets - Use `_cache_<dataset_name>` syntax in FROM clause - **load_dataset**: Load a dataset from a file or URL into the cache - Support for many common file formats - **get_dataset_sample**: Get a sample of rows from a dataset - Useful for previewing large datasets - **get_dataset_info**: Get detailed information about a dataset - Schema, row counts, column statistics, etc. - **remove_dataset**: Remove a dataset from the cache - **create_plot**: Create visualizations from datasets - Support for various plot types (line, bar, scatter, etc.) - **get_memory_usage**: Get detailed memory usage statistics ## Installation ```bash pip install arrow-cache-mcp ``` With optional dependencies: ```bash # For geospatial data support pip install "arrow-cache-mcp[geospatial]" # For enhanced visualization pip install "arrow-cache-mcp[viz]" # For all features pip in…