MCP Excel Reader

Name: MCP Excel Reader
Author: ArchimedesCrypto

@ArchimedesCrypto

关于 MCP Excel Reader

A Model Context Protocol (MCP) server for reading Excel files with automatic chunking and pagination support. Built with SheetJS and TypeScript.

#excel-reader #excel-files #data-processing

基本信息

分类

其他

许可证

MIT

运行时

node

传输方式

stdio

发布者

ArchimedesCrypto

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "excel-reader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@ArchimedesCrypto/excel-reader-mcp-chunked",
        "--client",
        "claude"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Excel Reader?

MCP Excel Reader is a Model Context Protocol (MCP) server for reading Excel files (.xlsx, .xls) with automatic chunking and pagination support. Built with SheetJS and TypeScript, it helps AI assistants and developers handle large Excel files efficiently by breaking them into manageable chunks.

How to use MCP Excel Reader?

Install the server globally via npm install -g @archimdescrypto/excel-reader or use Smithery for Claude Desktop. Add the server to your MCP settings file (e.g., ~/.config/claude/settings.json). Then invoke the read_excel tool with parameters filePath, sheetName, startRow, and maxRows to read Excel data.

Key features of MCP Excel Reader

Read Excel files with automatic size limits
Automatic chunking for large datasets
Sheet selection and row pagination
Proper date handling
Optimized for large files
Error handling and validation

Use cases of MCP Excel Reader

AI assistants reading large Excel spreadsheets piece by piece
Extracting data from specific sheets in multi-sheet workbooks
Paginating through rows of a large dataset without loading everything
Integrating Excel data into model context for AI-powered analysis

FAQ from MCP Excel Reader

What file formats does MCP Excel Reader support?

It supports .xlsx and .xls files.

How does chunking work?

The server automatically splits large files into chunks (default 100KB) and provides metadata for pagination, including hasMore and nextChunk information.