Data Wrangler (Polars) MCP server

Provides data preprocessing, transformation, and analysis capabilities using Polars dataframes for statistical operations on multiple file formats with structured JSON responses.
Back to servers
Provider
shibuiwilliam
Release date
Mar 30, 2025
Language
Python
Stats
2 stars

The MCP Data Wrangler server provides a standardized interface for data preprocessing, transformation, and analysis tasks within the Model Context Protocol ecosystem. It enables seamless integration of data wrangling operations such as data aggregation and descriptive statistics.

Installation

To use the MCP Data Wrangler server, follow these steps to set it up on your local machine:

  1. Clone the repository:
git clone https://github.com/yourusername/mcp-data-wrangler.git
cd mcp-data-wrangler
  1. You don't need to create a virtual environment for basic usage, but make sure you have the necessary dependencies installed.

Usage

Running with the MCP Inspector

You can launch the MCP inspector to debug and interact with the data wrangler:

npx @modelcontextprotocol/inspector uv --directory=src/mcp_data_wrangler run mcp-data-wrangler

After launching, the Inspector will display a URL in your terminal. Open this URL in your browser to begin debugging and using the data wrangler interface.

Adding as an MCP Server

To add this tool as an MCP server in your configuration:

  1. Add the following JSON configuration to your MCP server settings:
{
  "data-wrangler": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/mcp-data-wrangler",
      "run",
      "mcp-data-wrangler"
    ]
  }
}
  1. Replace /path/to/mcp-data-wrangler with the actual path where you cloned the repository.

Capabilities

The MCP Data Wrangler server provides the following data manipulation features:

  • Data aggregation: Combine data from multiple sources or perform grouping operations
  • Descriptive statistics: Generate statistical summaries of your datasets

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later