payroll-normalizer-mcp
Enables AI tools to normalize messy payroll spreadsheets (xlsx/xls/csv) into a standardized 10-column template for social insurance calculation, with automatic column detection, net-to-gross conversion, and cross-entity/month merging.
README
payroll-normalizer-mcp
让任意支持 MCP 的 AI 工具（Claude Code / Claude Desktop / Cursor / Windsurf / Cline / Zed / 支持 MCP 的 ChatGPT 等）都能把五花八门的工资表一键整理成「社保测算标准模板」。
把企业各种格式的工资表（.xlsx/.xls/.csv，多主体多月份）按"自然人跨主体跨月"归并，自动识别列名、把实发换算回应发(税前)，输出 10 列标准模板 + 整理报告。遇到非标表头时，AI 客户端可先 inspect_payroll 看表头样本、判断列含义，再带 overrides 调 normalize_payroll。
工具（MCP tools）
| 工具 | 作用 |
|---|---|
standard_columns |
返回标准 10 列定义、身份类型可选值、应发≠实发等口径（映射前先读） |
inspect_payroll(folder) |
逐文件返回表头、前 3 行样本、自动识别的字段映射、应发口径与问题 |
normalize_payroll(folder, output_dir?, overrides_json?) |
整理为标准模板 xlsx + 报告 md；overrides 修正非标表 |
generate_blank_template(output_path?) |
生成带下拉+说明的空白标准模板 |
安装：在各家工具里加这个 MCP server
无需先发布到 PyPI——用 uvx 直接从 GitHub 运行（需本机有 uv）。通用配置：
{
"mcpServers": {
"payroll-normalizer": {
"command": "uvx",
"args": ["--from", "git+https://github.com/dingxiang-me/payroll-normalizer-mcp", "payroll-normalizer-mcp"]
}
}
}
放到对应位置即可：
- Claude Code（一条命令）：
claude mcp add payroll-normalizer -- uvx --from git+https://github.com/dingxiang-me/payroll-normalizer-mcp payroll-normalizer-mcp - Claude Desktop：
claude_desktop_config.json→mcpServers（路径见 Settings › Developer）。 - Cursor：项目根
.cursor/mcp.json（或全局~/.cursor/mcp.json）→ 同上mcpServers。 - Windsurf：
~/.codeium/windsurf/mcp_config.json→ 同上。 - Cline / Zed / 其他：填到各自的 MCP 配置里，
command/args一致。
想更快启动可先发布到 PyPI，再把
args换成["payroll-normalizer-mcp"]。
用法
配置好后，直接对 AI 说：
「把
/path/to/工资表文件夹里的工资表整理成社保测算标准模板」
AI 会自动调用 inspect_payroll →（必要时）判断非标列 → normalize_payroll，在该文件夹产出 社保测算标准模板_整理结果.xlsx 和 整理报告.md。
依赖
- uv（提供
uvx） - 运行时自动拉取
mcp、openpyxl；旧版.xls另需xlrd（或先另存为 .xlsx）
配套
产出的标准模板可直接导入「社保公积金薪酬优化测算工具」做测算。本服务只做数据整理，不做社保/个税计算。
许可
MIT
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.