Powerful Model Context Protocol server offering advanced CSV data preprocessing, analysis, and visualization tools with customizable workflows and robust error handling for efficient data management.
Unlock the full potential of Vibe Preprocessing and Analysis MCP Server through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
A powerful MCP (Model Control Protocol) server for preprocessing and analyzing CSV files. This server provides a suite of tools for data manipulation, visualization, and analysis through an intuitive interface.
Data Loading and Management
Data Preprocessing
Data Analysis
Data Visualization
uv add "mcp[cli]" uv add pandas matplotlib seaborn numpy
mcp install server.py
If you prefer using pip:
pip install "mcp[cli]" pandas matplotlib seaborn numpy
uv run mcp
mcp dev server.py
You can install this server in Claude Desktop and interact with it right away by running:
mcp install server.py
Alternatively, you can test it with the MCP Inspector:
mcp dev server.py
send_work_dir()
: Retrieve the current working directoryset_work_dir(new_work_dir)
: Set a new working directorylist_work_dir_files()
: List files in the current working directoryload_csv(filename)
: Load a CSV file into the systemsave_global_df(filename)
: Save the current dataframe to a filehandle_column_mixed_types()
: Handle columns with mixed data typeshandle_null_values(strategy, columns)
: Handle null values in the dataset with various strategiesdrop_columns(columns)
: Remove specified columnsrename_columns(column_mapping)
: Rename columns in the dataframerun_custom_df_edit_code(code)
: Execute custom dataframe manipulation codedescribe_df()
: Generate a statistical summary of the dataframegenerate_correlation_matrix()
: Create a correlation matrix with visualizationplot_graph(graph_type, x_column, y_column, output_filename)
: Create various types of plots
run_custom_graph_code(code)
: Execute custom visualization codeWORK_DIR
: The working directory where files are read from and saved toThe server includes comprehensive error handling for:
Feel free to submit issues and enhancement requests!
Discover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!