npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

Iโ€™ve always been into building performant and accessible sites, but lately Iโ€™ve been taking it extremely seriously. So much so that Iโ€™ve been building a tool to help me optimize and monitor the sites that I build to make sure that Iโ€™m making an attempt to offer the best experience to those who visit them. If youโ€™re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, ๐Ÿ‘‹, Iโ€™m Ryan Hefnerย  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If youโ€™re interested in other things Iโ€™m working on, follow me on Twitter or check out the open source projects Iโ€™ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soonโ€“ish.

Open Software & Tools

This site wouldnโ€™t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you ๐Ÿ™

ยฉ 2026 โ€“ย Pkg Stats / Ryan Hefner

@iflow-mcp/ishayoyo-excel-mcp

v1.0.0

Published

๐Ÿš€ The Ultimate Data Science MCP Server - Advanced statistical analysis, ML preprocessing, and data visualization for Excel & CSV files

Downloads

44

Readme

Excel MCP Server

An MCP server that brings Excel/CSV data analysis capabilities to Claude, with a custom-built formula engine and AI-powered features.

What makes this different: The world's first conversational data analysis MCP server powered by HyperFormula (395 Excel functions) + multi-provider AI. Ask questions in natural language and get instant insights from your Excel/CSV files. Built for analysts who want AI-powered conversations with their data, not just spreadsheet manipulation.

How It Works

This server acts as a bridge between Claude and your data files, providing:

  1. Formula Engine: A complete Excel-compatible formula parser and evaluator built from scratch, supporting 82 functions with proper operator precedence and dependency tracking.

  2. Data Operations: Direct read/write access to CSV and Excel files with intelligent parsing and type detection.

  3. AI Integration: Multi-provider AI support that intelligently routes requests to the best available AI service for natural language processing and formula generation.

  4. Bulk Processing: Parallel operations across multiple files for improved performance on large datasets.

Features

  • 395 Excel functions via HyperFormula (battle-tested library)
  • AI-powered natural language data queries
  • Multi-provider AI support (Anthropic, OpenAI, DeepSeek, Gemini)
  • Large file support with intelligent chunking for files >100MB
  • Bulk operations across multiple files (3x faster)
  • Smart data validation and consistency checking
  • Advanced statistical analysis and data profiling
  • Formula evaluation with dependency tracking
  • Pivot tables and aggregation
  • Cross-file referential integrity validation
  • Excel styling and formatting with auto-fitting columns and cell formatting

๐Ÿข CFO-Level Financial Analysis

  • DCF Valuation Models - Complete discounted cash flow analysis with NPV, IRR, terminal value
  • Financial Ratio Analysis - Comprehensive ratios with industry benchmarks (liquidity, profitability, leverage)
  • Budget Variance Analysis - Automated budget vs actual comparisons with variance reporting
  • Scenario Modeling - What-if analysis with multiple assumption scenarios
  • Financial Functions - NPV, IRR, PMT, FV, PV, RATE, depreciation schedules, and more
  • Industry Benchmarking - Automatic comparison against industry standards

Installation

git clone https://github.com/ishayoyo/excel-mcp.git
cd excel-mcp
npm install
npm run build

Claude Code Setup

Option 1: Direct MCP Configuration

# Add to Claude Code
claude mcp add excel-csv "node" "C:/path/to/excel-mcp/dist/index.js"

Option 2: Global Install

npm install -g .
# Then configure in Claude Code with:
# Command: npx
# Args: -y excel-csv-mcp

Cursor Claude Desktop Setup

Option 1: Direct MCP Configuration

Edit your Cursor MCP configuration file (%APPDATA%\Cursor\mcp.json on Windows, ~/Library/Application Support/Cursor/mcp.json on macOS):

{
  "mcpServers": {
    "excel-csv": {
      "command": "node",
      "args": ["C:/path/to/excel-mcp/dist/index.js"]
    }
  }
}

Replace C:/path/to/excel-mcp/dist/index.js with the actual path to your built dist/index.js file.

Option 2: Using npx (Recommended)

{
  "mcpServers": {
    "excel-csv": {
      "command": "npx",
      "args": ["-y", "excel-csv-mcp"]
    }
  }
}

This requires a global npm install:

npm install -g .

AI Providers

Create a .env file with your API keys:

cp .env.example .env
ANTHROPIC_API_KEY=your-key-here
OPENAI_API_KEY=your-key-here
DEEPSEEK_API_KEY=your-key-here
GEMINI_API_KEY=your-key-here

Supported providers: Anthropic, OpenAI, DeepSeek, Gemini, Local fallback

Usage Examples

Ask questions in natural language:

  • "What's the total revenue in sales_data.csv?"
  • "Sum all sales where region is 'North'"
  • "Find duplicates in customer_data.xlsx"
  • "Clean messy customer data - fix phone numbers and names"
  • "Remove duplicate rows from my contact list"
  • "Help me VLOOKUP customer details between two files"
  • "Generate a formula to calculate average of last 30 days"
  • "Validate data consistency between sales.xlsx and branches.xlsx"
  • "Create a pivot table by department and export to report.xlsx"
  • "Analyze this 500MB dataset in chunks to avoid memory issues"
  • "Get file info and optimal chunk size for large_dataset.csv"

Available Tools

Core Operations

  • read_file - Read CSV/Excel files (supports offset/limit for large files)
  • read_file_chunked - Stream large files in manageable chunks to avoid memory limits
  • get_file_info - Analyze file size and get chunking recommendations for large datasets
  • get_cell / get_range - Access specific cells or ranges
  • search / filter_rows - Find and filter data
  • aggregate - SUM, AVG, COUNT, MIN, MAX operations

Excel Workflow Tools (NEW)

  • find_duplicates - Smart duplicate detection and removal with multiple strategies
  • data_cleaner - Batch data cleaning operations (trim whitespace, fix phones, standardize names, etc.)
  • vlookup_helper - Intelligent VLOOKUP setup with fuzzy matching and error handling

Bulk Operations

  • bulk_aggregate_multi_files - Aggregate across multiple files (3x faster)
  • bulk_filter_multi_files - Filter multiple files simultaneously

Formula Engine

  • evaluate_formula - Execute Excel formulas
  • parse_natural_language - Convert text to formulas
  • explain_formula - Explain formula functionality

Analytics

  • statistical_analysis - Comprehensive statistics
  • correlation_analysis - Find relationships between columns
  • data_profile - Complete data profiling
  • pivot_table - Group and aggregate data

AI Features

  • smart_data_analysis - AI-powered analysis suggestions
  • ai_provider_status - Check AI provider availability

Styling & Formatting

  • format_cells - Apply fonts, colors, borders, alignment to Excel cells
  • auto_fit_columns - Automatically adjust column widths to fit content
  • write_multi_sheet - Create complex Excel files with formulas and formatting

Validation & Export

  • validate_data_consistency - Cross-file data integrity checks
  • write_file / export_analysis - Create and export files

Key Features

๐Ÿค– AI-Powered Intelligence

  • Ask "What's the correlation between sales and marketing spend?" โ†’ Gets instant statistical analysis
  • Say "Find all customers who spent over $1000 last quarter" โ†’ AI generates complex formulas automatically
  • Request "Explain what this VLOOKUP formula does" โ†’ Gets plain English explanation

โšก Bulk Data Processing

  • "Sum total revenue across 10 quarterly files" โ†’ Processes in parallel (3x faster than manual)
  • "Find all employees with 'Manager' in their title across 5 HR spreadsheets" โ†’ Multi-file search
  • "Aggregate sales data from Q1, Q2, Q3, Q4 files into one report" โ†’ Automated consolidation

๐Ÿงฎ Programmatic Formula Engine

  • Evaluates =SUMIFS(C:C, A:A, ">=1/1/2024") without Excel installed
  • Computes complex nested formulas with proper precedence
  • Handles circular references and dependency tracking
  • 82 functions implemented programmatically

๐Ÿ“Š Advanced Analytics

  • Comprehensive statistical profiling of every column
  • Correlation analysis between any numeric columns
  • Smart data quality validation across multiple files
  • Automated outlier detection and data consistency checks

๐Ÿ” Smart Cross-File Operations

  • "Validate that all customer IDs in sales.xlsx exist in customers.xlsx"
  • "Check for duplicate emails across 3 contact lists"
  • "Find missing data between related spreadsheets"
  • Referential integrity validation (like database foreign keys but for spreadsheets)

๐ŸŽฏ Natural Language Data Conversations

  • "Show me the top 10 products by revenue" โ†’ AI understands intent and executes
  • "Calculate average order value for customers from California" โ†’ Generates optimal query
  • "Create a summary of sales trends by month" โ†’ Suggests best analysis approach

๐Ÿ“ˆ Large File Processing (NEW)

  • Intelligent Chunking: Automatically handles files >100MB without memory errors
  • Smart Recommendations: get_file_info analyzes files and suggests optimal chunk sizes
  • Seamless Navigation: Read any chunk with proper headers and metadata
  • Memory Efficient: Constant memory usage regardless of file size (tested up to 1M+ rows)
  • Progress Tracking: Chunk navigation with hasNext/hasPrevious indicators

Why This Approach Matters

Traditional Excel tools focus on file manipulation - reading, writing, formatting. They treat spreadsheets as static documents.

This server treats your data as a dynamic knowledge base you can have conversations with. It's not about pretty formatting - it's about CFO-level financial modeling, strategic analysis, and executive decision-making powered by AI.

Built for CFOs, financial analysts, and executives who need: ๐Ÿ’ฐ DCF valuations and investment analysis ๐Ÿ“Š Financial ratio analysis with benchmarks ๐ŸŽฏ Scenario planning and risk modeling ๐Ÿ’ผ Budget variance tracking and reporting ๐Ÿค– AI-powered financial insights at conversational speed

License

MIT