Abacus
An MCP server for local Excel automation, providing 88 tools for reading, manipulating, and analyzing Excel files. It supports .xlsx, .xls, and .csv formats, with a unique nine-chapter classification system.
README
Abacus（算盘）
本地 Excel 自动化框架，以中国算学文化为命名体系。
项目状态
| 指标 | 数值 |
|---|---|
| 核心能力 | 84 个 |
| 测试用例 | 437 个（全部通过，7 跳过） |
| MCP 工具 | 88 个 |
| CLI 命令 | 66 个 |
| 知识库文件 | 29 个 |
| 测试覆盖率 | 81% |
特性
- 84 个通用 Excel 操作能力
- 九章分类（方田、粟米、衰分、少广、商功、均输、盈不足、方程、勾股）
- CLI + MCP Server + Python 库三种使用方式
- SKILL.md 文档驱动的 Skill 引擎
- 支持 .xlsx、.xls、.csv 格式
- CodeGraph 代码知识图谱
- SkillIndexer 知识库索引器
安装
pip install abacus
快速开始
CLI 使用
# 查看帮助
abacus --help
# 读取数据
abacus read -f data.xlsx -s Sheet1 -r A1:D10
# 查看结构
abacus structure -f data.xlsx
# 列出所有能力
abacus capabilities
Python 库使用
from abacus.core import MeasureRangeCapability
cap = MeasureRangeCapability()
result = cap.execute(None, file="data.xlsx", sheet="Sheet1", range="A1:D10")
print(result)
MCP Server 使用
# 启动 MCP Server
python -m abacus.mcp_server
九章分类
| 章节 | 英文 | 能力数 | 说明 |
|---|---|---|---|
| 方田章 | Field | 12 | 数据读取、单元格操作、工作表管理 |
| 粟米章 | Grain | 7 | 格式转换、类型转换、单位转换、数据清洗、转置、分列 |
| 衰分章 | Share | 6 | 分组、分配、汇总、透视分析、透视向导、分类汇总 |
| 少广章 | Dimension | 3 | 反向计算、推导、计算 |
| 商功章 | Work | 29 | 批量操作、图表、透视表、表格、工作流、样式、批注、冻结、筛选、隐藏、分组、保护、缩放、打包 |
| 均输章 | Transport | 5 | 导入导出、迁移、合并、Markdown转换 |
| 盈不足章 | Balance | 7 | 数据验证、代码审计、文件审计、文件验证 |
| 方程章 | Equation | 7 | 公式创建、解方程、计算、公式生成、公式诊断、公式重算、自动求和 |
| 勾股章 | Triangle | 8 | 统计分析、趋势分析、相关性分析、数据分析、可视化、差异分析、高级分析 |
文档
许可证
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.