sbroenne/mcp-server-excel
Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.
What it solves
ExcelMcp allows AI agents (such as Claude, ChatGPT, and GitHub Copilot) to control the actual Microsoft Excel application on Windows. Unlike tools that simply parse files, this project provides a way for AI to perform complex operations like refreshing Power Query, running VBA or Python in Excel, and managing PivotTables and charts while preserving the workbook's formatting and data model.
How it works
The project implements the Model Context Protocol (MCP) and a token-efficient CLI. It acts as a bridge between an AI assistant and the official Microsoft Excel COM API. When an AI agent sends a request in natural language, the server translates these requests into specific commands that drive the real Excel application in real-time.
Who it’s for
Users on Windows who use Microsoft Excel 2016 or later and want to automate their spreadsheets using natural language via AI agents or scripts.
Highlights
Direct Application Control: Drives the actual Excel app via COM API rather than just editing files.
Comprehensive Toolset: Includes 31 tools with 325 operations covering data analytics, cells, workbooks, charts, and advanced automation.
Multi-Interface Support: Offers an MCP Server for conversational assistants and a CLI for coding agents and scripts to reduce token usage.
Advanced Feature Support: Capable of handling Power Query, DAX, Power Pivot, Goal Seek, and Python
=PY()functions.
Related
- Project
- Project
- Project
- Project
- Project