Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/samcil/excel-mcp-server/claude-mdgit clone --depth 1 https://github.com/Samcil/excel-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/samcil/excel-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/samcil/excel-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/samcil/excel-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00827 | $0.00827 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
excel-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
97% identical to excel-mcp-server CLAUDE.md — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an Excel MCP (Model Context Protocol) Server that enables AI assistants to interact with Microsoft Excel files. It provides a bridge between AI models and Excel spreadsheets for programmatic data manipulation.
Development Commands
Build and Development
npm run build # Build Go binaries + compile TypeScript
npm run watch # Watch TypeScript files for changes
npm run debug # Debug with MCP inspector
Testing
go test ./... # Run all Go tests
go test ./internal/tools -v # Run specific package tests
go test -run TestReadSheetData ./internal/tools # Run specific test
Linting and Formatting
go fmt ./... # Format Go code
go vet ./... # Vet Go code for issues
Architecture
Core Components
Dual Backend Architecture: The server supports two Excel backends:
- Windows: OLE automation for live Excel interaction (
excel_ole.go) - Cross-platform: Excelize library for file operations (
excel_excelize.go)
Key Interfaces:
ExcelInterfaceininternal/excel/excel.go- Unified Excel operations APIToolinterface ininternal/tools/- MCP tool implementations
Entry Points:
cmd/office-mcp-server/main.go- Go binary entry pointlauncher/launcher.ts- Cross-platform launcher that selects appropriate binary
Tool System
MCP tools are implemented in internal/tools/:
excel_describe_sheets- List worksheets and metadataexcel_read_sheet- Read sheet data with paginationexcel_write_to_sheet- Write data to sheetsexcel_create_table- Create Excel tablesexcel_copy_sheet- Copy sheets between workbooksexcel_screen_capture- Windows-only screenshot functionality
Pagination System
Large datasets are handled through configurable pagination:
- Default limit: 4000 cells
- Configurable via
EXCEL_MCP_PAGING_CELLS_LIMITenvironment variable - Implemented in
internal/excel/pagination.go
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 123 lines · 827 tokens per session scan A 24ac5befa5f7
excel-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Samcil/excel-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 827 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to excel-mcp-server CLAUDE.md, differing in 20 lines, and is treated as a copy.
Other instructions, from other repositories
mcp-google-sheets CLAUDE.md
Claude Code instructions for toantran201/mcp-google-sheets, covering claude.md, commands, architecture, adding or renaming a tool and auth scope is derived from enabled tools.
wechat-mcp-friend-automation CLAUDE.md
Claude Code instructions for zbvxbb622-code/wechat-mcp-friend-automation, covering claude 系统提示词(wechat mcp), excel 加好友工具使用规则: and replytomessagesbychat 使用规则:.
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
Excel-Power-Pivot-MCP CLAUDE.md
Instructions for back1ply/Excel-Power-Pivot-MCP, covering claude.md, project overview, build and test commands, build and debug build.
markdown_everything CLAUDE.md
Instructions for wokaka209/markdown_everything, covering claude.md, 项目概述, 常用命令, 基本转换 and 直接用 markitdown cli.
ExcelMCPAdvanced CLAUDE.md
Claude Code instructions for nitishkthakur/ExcelMCPAdvanced, covering excel mcp server — claude guidance, project layout, development commands, key design rules and how to use the mcp tools (for analysis tasks).