Quick Data for Windows MCP MCP Server

A Windows-optimized server for performing data analytics on JSON and CSV files, designed for Claude Desktop integration.

Windows-optimized fork ofdisler/quick-data-mcpfor Claude Desktop

Universal data analytics capabilities for JSON/CSV files - now working seamlessly on Windows!

This is aWindows-optimized forkof the excellent quick-data-mcpproject by @disler.

The original project provides powerful MCP server capabilities for data analytics, and this fork specifically addresses Windows compatibility issues and Claude Desktop integration challenges.

This is my first ever try at this. Please feel free to give suggestions and or criticisms. I loved the quick data mcp for claude code. There was nothing available like it for claude desktop so with the help of claude code we now have it.

- ✅Windows Path Handling- Proper Windows file path support
- ✅Claude Desktop Ready- Pre-configured batch launchers and setup
- ✅Dependency Management- Automated installation scripts
- ✅Troubleshooting- Complete guides for common Windows issues

- Universal Data Support- Works with any CSV/JSON file structure
- Windows Path Optimization- Handles Windows file paths correctly
- Claude Desktop Integration- Pre-configured for seamless setup
- Automatic Schema Discovery- Analyzes your data and suggests analyses
- 32+ Analytics Tools- From basic stats to advanced ML features
- Interactive Visualizations- Create charts with Plotly
- Memory Management- Optimized for large datasets

- Windows 10/11
- Python 3.9+(Download here)
- Claude Desktop(Download here)

git clone https://github.com/Beaulewis1977/quick-data-for-windows-mcp.git cd quick-data-for-windows-mcp

Copy the fixed configuration to Claude Desktop:

copy claude_desktop_config_fixed.json "%APPDATA%\Claude\claude_desktop_config.json"

IMPORTANT:Edit the config file and update thecwdpath to your actual installation directory.

If you seeModuleNotFoundError: No module named 'mcp', check the TROUBLESHOOTING.mdguide.

Once configured, start with this slash command in Claude Desktop:

Load my sales data: C:\Users\YourName\Documents\sales_data.csv as "sales"

Show me correlations in the sales dataset Create a bar chart of sales by region Analyze the distribution of revenue column

Validate data quality for sales dataset Compare sales dataset with marketing dataset Generate dashboard with revenue trends and regional breakdown

- load_dataset- Load CSV/JSON files with automatic schema discovery
- list_loaded_datasets- View all datasets in memory
- get_dataset_info- Get detailed dataset information
- clear_dataset/clear_all_datasets- Memory management

- segment_by_column- Analyze categorical data segments
- find_correlations- Discover relationships between variables
- analyze_distributions- Statistical distribution analysis
- detect_outliers- Identify data anomalies
- suggest_analysis- AI-powered analysis recommendations

- create_chart- Generate interactive charts (bar, scatter, line, histogram)
- generate_dashboard- Multi-chart dashboards

- validate_data_quality- Comprehensive data quality scoring
- compare_datasets- Multi-dataset comparison analysis
- merge_datasets- Join datasets with flexible strategies
- calculate_feature_importance- ML feature importance analysis
- export_insights- Export results in multiple formats

- Standard CSV with headers
- Custom delimiters automatically detected
- UTF-8 encoding support
- Large file handling with sampling options

- Flat JSON structures
- Nested JSON (automatically flattened)
- JSON Lines format
- Array of objects format

If the automatic setup doesn't work, manually edit your Claude Desktop config:

Location:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "quick-data-windows": { "command": "python", "args": [ "C:\\path\\to\\your\\quick-data-for-windows-mcp\\main.py" ], "cwd": "C:\\path\\to\\your\\quick-data-for-windows-mcp", "env": { "LOG_LEVEL": "INFO", "PYTHONPATH": "C:\\path\\to\\your\\quick-data-for-windows-mcp\\src" } } } }

If you prefer UV (recommended for Python dependency management):

{ "mcpServers": { "quick-data-windows": { "command": "uv", "args": [ "--directory", "C:\\path\\to\\your\\quick-data-for-windows-mcp", "run", "python", "main.py" ] } } }

Test the server standalone (before Claude Desktop integration):

Quick Data for Windows MCP v1.0.0 Server running on stdio...

1. Load sales_data.csv as "sales" 2. Show correlations in sales dataset 3. Create bar chart of sales by product_category 4. Detect outliers in revenue column 5. Generate dashboard with top products and regional trends

1. Load customer_data.csv as "customers" 2. Validate data quality for customers dataset 3. Analyze distributions for age column 4. Segment by customer_type column

- Ensure Python is in your PATH
- Runpip install -r requirements.txtmanually
- Check that PYTHONPATH is set correctly in config

- Use full Windows paths:C:\Users\...
- Avoid relative paths like.\data\file.csv
- Check file permissions

- Restart Claude Desktop after config changes
- Check config file syntax with JSON validator
- Verify file paths are correct (no typos)
- Check that Python 3.9+ is installed:python --version
- Verify dependencies:pip list | findstr pandas
- Test server manually:python main.py
- Check Claude Desktop logs for errors

This is a community-driven Windows adaptation of the original quick-data-mcp project. Contributions welcome!

# Clone and setup git clone https://github.com/Beaulewis1977/quick-data-for-windows-mcp.git cd quick-data-for-windows-mcp # Install development dependencies pip install -r requirements.txt pip install pytest black ruff # Run tests (when implemented) pytest tests/

MIT License - see LICENSE file for details.

This project is a Windows-optimized fork of the originalquick-data-mcpby @disler.

- Original Author:@disler
- Original Repository:disler/quick-data-mcp
- Original Purpose:MCP server for data analytics with Claude Code
- License:MIT (maintained in this fork)

- Windows Compatibility:@Beaulewis1977
- Claude Desktop Integration:Community-driven improvements
- Troubleshooting & Documentation:Enhanced for Windows users

- Model Context Protocol:Anthropic
- Data Processing:pandas, numpy, plotly, scikit-learn
- Platform:Optimized for Windows + Claude Desktop

- Original Project- For the core innovation
- This Fork- For Windows support

Special thanks to @dislerfor creating the foundational work that made this Windows adaptation possible!

- Claude Desktop
- Model Context Protocol
- Original Quick Data MCP
- Python for Windows

Ready to analyze your data with AI? Load a CSV and start exploring! 🚀

Manage multiple Fireproof JSON document databases with cloud sync capabilities.

Query local CSV, Parquet, JSON and TSV files with real SQL via DuckDB. Gives your AI coding tool ground-truth data access instead of hallucinated answers.

Query a folder of CSV / Parquet / JSON files with SQL via DuckDB — read-only and sandboxed; scattered files become one queryable source.

Official MCP server for dbt (data build tool) providing integration with dbt Core/Cloud CLI, project metadata discovery, model information, and semantic layer querying capabilities.

Provides AI assistants with a secure and structured way to explore and analyze data in GreptimeDB.

Build robust data workflows, integrations, and analytics on a single intuitive platform.

Query and analyze data with MotherDuck and local DuckDB

An MCP server that provides tools to interact with Powerdrill datasets, enabling smart AI data analysis and insights.

Slingshot MCP introduces Slingshot Aerospace’s space data platform in your AI chat—explore satellites, orbits, and Portal insights through Slingshot’s hosted server.

Quick Data for Windows MCP

About

Details

Jump to

Setup

About

Details

Jump to

Setup

More like this

Sequential Thinking

Redis

Filesystem

EverArt

Google Drive

Sqlite