Claude MCP Data Explorer for Windows

Claude MCP Data Explorer for Windows

By tofunori GitHub

Windows MCP server for data exploration with Claude

Overview

What is Claude MCP Data Explorer?

Claude MCP Data Explorer is a TypeScript implementation of a Model Context Protocol (MCP) server designed for data exploration with Claude. It allows users to load CSV files and execute JavaScript data analysis scripts for advanced data analysis.

How to use Claude MCP Data Explorer?

To use the server, first install the prerequisites including Node.js and Claude Desktop. Clone the repository, install dependencies, build the project, and run the setup script. After setup, start Claude Desktop, select the "Explore Data" prompt template, and enter the CSV file path and exploration topic.

Key features of Claude MCP Data Explorer?

  • Load CSV data into memory for analysis.
  • Execute JavaScript code for data processing and analysis.
  • Structured data exploration process with prompt templates.
  • Efficient handling of large files using chunking.

Use cases of Claude MCP Data Explorer?

  1. Analyzing sales trends from CSV data.
  2. Performing data processing and visualization tasks.
  3. Automating data insights generation for various datasets.

FAQ from Claude MCP Data Explorer?

  • What are the prerequisites for using Claude MCP Data Explorer?

You need Node.js v16+ and Claude Desktop installed.

  • How do I troubleshoot if Claude doesn't show the MCP server?

Check the configuration file and ensure it points to the compiled JavaScript file. Rebuild the project if necessary.

  • Is there a license for Claude MCP Data Explorer?

Yes, it is licensed under the MIT License.

Content

Claude MCP Data Explorer for Windows

A TypeScript implementation of a Model Context Protocol (MCP) server for data exploration with Claude. This server integrates with Claude Desktop and enables advanced data analysis by providing tools to load CSV files and execute JavaScript data analysis scripts.

Prerequisites

Installation (Updated for Windows)

  1. Clone this repository

    git clone https://github.com/tofunori/claude-mcp-data-explorer.git
cd claude-mcp-data-explorer

  2. Install dependencies

    npm install

  3. Build and run setup script

    npm run setup

    This will:

    • Build the TypeScript code to JavaScript
    • Configure Claude Desktop to use the compiled JavaScript
    • Create necessary directories

  4. Restart Claude Desktop and enable Developer Mode

    • Close Claude Desktop completely
    • Start Claude Desktop
    • Go to Help → Enable Developer Mode

Manual Testing

You can test the server directly by running:

npm run build
npm run start

The server should start without errors. If you can run this successfully, Claude Desktop should be able to use the server as well.

How It Works

This MCP server provides two main tools for Claude:

  1. load-csv - Loads CSV data into memory for analysis
  2. run-script - Executes JavaScript code for data processing and analysis

It also includes a prompt template that guides Claude through a structured data exploration process.

Usage

  1. Start Claude Desktop

  2. Select the "Explore Data" prompt template

    • This prompt will appear in Claude Desktop after setup

  3. Enter CSV file path and exploration topic

    • Example file path: C:/Users/YourName/Documents/data.csv
    • Example topic: "Sales trends by region"

  4. Let Claude analyze your data

    • Claude will load the CSV file and generate insights automatically
    • The server handles large files efficiently using chunking

Troubleshooting

  1. Claude doesn't show the MCP server

    • Check the configuration file at %APPDATA%\Claude\claude_desktop_config.json
    • It should point to the compiled JavaScript file in the dist directory
    • Try rebuilding the project with npm run build
    • Enable Developer Mode and check the MCP Log File (Developer → Open MCP Log File)
    • Use Developer → Reload All MCP Servers to force refresh

  2. Permission errors reading files

    • Make sure Claude has access to the CSV file location
    • Try using absolute paths with forward slashes (/) or escaped backslashes (\\)

  3. JavaScript errors in scripts

    • Check that your script is compatible with the allowed modules
    • Review any error messages in Claude's response

License

MIT License - see LICENSE file for details.

Acknowledgments

  • Based on the official MCP TypeScript SDK from Anthropic
  • Thanks to the MCP community for examples and inspiration
No tools information available.
No content found.