This project provides a Model Context Protocol (MCP) server for interacting with Microsoft Excel files, enabling programmatic reading and writing of data and formulas. It is designed for developers and researchers who need to integrate Excel workflows into automated systems or AI agents, offering a bridge between Excel's tabular data and external applications.

How It Works

The server leverages Node.js and the xlsx library to handle .xlsx, .xlsm, .xltx, and .xltm file formats. It exposes commands for describing sheets, reading/writing cell values and formulas, creating new sheets, and even capturing screenshots of specific ranges (Windows only). The architecture allows for configuration via environment variables, such as EXCEL_MCP_PAGING_CELLS_LIMIT, to control data handling.

Quick Start & Requirements

• Installation: Add to MCP server configuration:
  • Windows: npx --yes @negokaz/excel-mcp-server
  • Other platforms: npx --yes @negokaz/excel-mcp-server
• Prerequisites: Node.js 20.x or later.
• Resources: No specific hardware requirements mentioned beyond Node.js.
• Docs: https://github.com/negokaz/excel-mcp-server

Highlighted Details

• Supports reading and writing text values and formulas.
• Enables creation of new sheets and tables within Excel files.
• Includes a excel_screen_capture tool for generating image previews of sheet ranges (Windows only).
• Provides tools for copying sheets and describing sheet metadata.

Maintenance & Community

The project is maintained by Kazuki Negoro. No specific community channels or roadmap details are provided in the README.

Licensing & Compatibility

• License: MIT License.
• Compatibility: Permissive MIT license allows for commercial use and integration into closed-source projects.

Limitations & Caveats

The excel_screen_capture functionality is explicitly limited to Windows operating systems. The README does not detail performance benchmarks or specific limitations regarding very large Excel files beyond the configurable paging limit.