MCP.so
Sign In

Vibe Preprocessing and Analysis MCP Server for CSV files

@mudit14224

Repository

About Vibe Preprocessing and Analysis MCP Server for CSV files

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.

#data-analysis#csv-processing#data-visualization

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Vibe-Data-Analysis": {
      "command": "uv",
      "args": [
        "run",
        "mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Vibe Preprocessing and Analysis MCP Server for CSV files?

Vibe Preprocessing and Analysis MCP Server for CSV files is an MCP (Model Control Protocol) server that provides tools for loading, cleaning, analyzing, and visualizing CSV data. It integrates with Claude Desktop and other MCP hosts, and is built on Python with pandas, matplotlib, seaborn, and numpy. It is intended for users who need to preprocess tabular data and generate plots directly through an MCP interface.

How to use Vibe Preprocessing and Analysis MCP Server for CSV files?

Install dependencies with uv add "mcp[cli]" pandas matplotlib seaborn numpy (or pip), then run mcp install server.py to register the server in Claude Desktop. Use mcp dev server.py to test with the MCP Inspector. Set the working directory via the set_work_dir tool or the WORK_DIR environment variable. Use the provided tools in natural language or through the inspector to load, preprocess, analyze, and visualize CSV files.

Key features of Vibe Preprocessing and Analysis MCP Server for CSV files

  • Load CSV files and manage working directories
  • Handle null values with multiple strategies (remove, fill, forward/backward fill)
  • Drop and rename columns, run custom DataFrame editing code
  • Generate statistical summaries and correlation matrices with visualizations
  • Create nine types of plots (line, bar, scatter, histogram, box, violin, pie, count, KDE)
  • Save processed DataFrames and visualizations to the working directory

Use cases of Vibe Preprocessing and Analysis MCP Server for CSV files

  • Clean and prepare messy CSV datasets by handling mixed data types and null values
  • Explore data structure and generate summary statistics and correlation heatmaps
  • Create publication-ready visualizations for exploratory data analysis
  • Automate custom data transformation and plotting logic through code execution
  • Integrate CSV data tasks into an MCP-enabled assistant workflow (e.g., Claude Desktop)

FAQ from Vibe Preprocessing and Analysis MCP Server for CSV files

What are the required dependencies?

Python 3.x, pandas, matplotlib, seaborn, numpy, and the mcp[cli] package. The recommended package manager is uv, but pip also works.

How do I set the working directory for file operations?

Use the set_work_dir(new_work_dir) tool or set the WORK_DIR environment variable before starting the server.

Which plot types are supported?

The plot_graph tool supports: line, bar, scatter, hist (histogram with KDE), box, violin, pie, count, and kde.

How can I handle null values in my dataset?

Use the handle_null_values(strategy, columns) tool. Supported strategies: remove rows, fill with mean, median, or mode, forward fill, backward fill, or fill with a constant value.

Can I run my own code for data manipulation or graphing?

Yes. Use run_custom_df_edit_code(code) to modify the DataFrame and run_custom_graph_code(code) to generate custom plots. Errors in custom code are caught and reported.

Frequently asked questions

What are the required dependencies?

Python 3.x, pandas, matplotlib, seaborn, numpy, and the `mcp[cli]` package. The recommended package manager is uv, but pip also works.

How do I set the working directory for file operations?

Use the `set_work_dir(new_work_dir)` tool or set the `WORK_DIR` environment variable before starting the server.

Which plot types are supported?

The `plot_graph` tool supports: line, bar, scatter, hist (histogram with KDE), box, violin, pie, count, and kde.

How can I handle null values in my dataset?

Use the `handle_null_values(strategy, columns)` tool. Supported strategies: remove rows, fill with mean, median, or mode, forward fill, backward fill, or fill with a constant value.

Can I run my own code for data manipulation or graphing?

Yes. Use `run_custom_df_edit_code(code)` to modify the DataFrame and `run_custom_graph_code(code)` to generate custom plots. Errors in custom code are caught and reported.

Comments

Basic information

Category

Data & Analytics

Transports

stdio

Author

mudit14224

More Data & Analytics MCP servers

World Monitor

Elie Habib

Live global-intelligence MCP server covering news, markets, conflicts, aviation, maritime activity, energy, climate, cyber threats, supply chains, and source-grounded regional briefs.

ScrapeCheck

FieldmodeLLC

Verify scraped data against the live source page. Signed verdicts, $0.01 via x402.

Bounce Watch - Company Signal Intelligence

bouncewatch

Bounce Watch tells you what just changed at a company, and when. Who raised money. Who hired a senior person. Who opened an office, won a customer, or announced a partnership. Every event carries its own date, so you ca

Sugra API MCP

Sugra Systems, Inc.

Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl

1

Hologrow

Hologrow Inc

Hologrow is the e-commerce data layer for any AI