一个用Python编写的小型模型上下文协议服务器，为Claude提供了十二种处理项目文件夹的工具：列出、搜索、读取、编辑和分析文件、生成......
概览
一个用 Python 编写的小型模型上下文协议服务器，为 Claude 提供了十二种处理项目文件夹的工具：列出、搜索、读取、编辑和分析文件、生成 Markdown 输出、保存笔记以及只读 git 信息。 为大学课程项目开发，使用官方 mcp Python SDK（版本 1.x，FastMCP 风格）。它在 127.0.0.1 上为 MCP 提供服务。claude.ai 通过固定地址访问，小型看门狗脚本保持服务器和隧道运行。 Notes/ 是在 write_note（或保存的报告）首次写入文件时创建的。.trash/ 保存被 delete_file 移除的文件。logs/ 保存看门狗输出。测试使用临时文件夹，之后删除。 1. 从 https://www.python.org/downloads/ 下载 Python 3.10 或更新版本 2.在安装程序中，点击安装前先勾选。3. 打开一个新的命令提示符，勾选：python --version requirements.txt mps mp>=1.8.0，<2。可流式 HTTP 需要 1.8 或更新版本，版本 2。
概述（AI 翻译）
一个用 Python 编写的小型模型上下文协议服务器，为 Claude 提供了十二种处理项目文件夹的工具：列出、搜索、读取、编辑和分析文件、生成 Markdown 输出、保存笔记以及只读 git 信息。
为大学课程项目开发，使用官方 mcp Python SDK（版本 1.x，FastMCP 风格）。它通过 [127.0.0.1 上的 可流式 HTTP 提供 MCP。claude.ai 通过固定的 ngrok 地址访问，小型看门狗脚本保持服务器和隧道运行。
它的作用
| 工具 | 它的作用 | 写入文件吗？ |
|---|---|---|
list_project_files |
列出文件大小和最后修改日期，并可选副名过滤器 | 无 |
analyze_text_file |
字数、行数、阅读时间和前十名关键词 | 无 |
search_in_files |
跨文本文件、文件号和行号的大小写不区分关键词搜索 | 无 |
generate_markdown_toc |
从.md文件的标题构建Markdown目录 |
否 |
generate_project_report |
Markdown 摘要：按文件类型、总大小、最大和最新文件计数 | 仅当 save_as 给出时 |
write_note |
创建一个新的.md或’。 |
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
workspace-assistant (MCP server)
A small Model Context Protocol server, written in Python, that gives Claude twelve tools for working with a project folder: listing, searching, reading, editing and analyzing files, generating Markdown output, saving notes, and read-only git information.
Built for a university course project using the official mcp Python SDK (version 1.x, FastMCP style). It serves MCP over streamable HTTP on 127.0.0.1. claude.ai reaches it through a fixed ngrok address, and small watchdog scripts keep the server and tunnel running.
What it does
| Tool | What it does | Writes files? |
|---|---|---|
list_project_files |
Lists files with size and last-modified date, with an optional extension filter | No |
analyze_text_file |
Word count, line count, reading time and top 10 keywords | No |
search_in_files |
Case-insensitive keyword search across text files, with file and line numbers | No |
generate_markdown_toc |
Builds a Markdown table of contents from a .md file’s headings |
No |
generate_project_report |
Markdown summary: counts by file type, total size, largest and newest files | Only if save_as is given |
write_note |
Creates a new .md or .txt file in notes/ |
Yes (new files only) |
find_todos |
Lists TODO, FIXME and NOTE comments with file and line number |
No |
find_broken_links |
Reports relative links in a .md file that point to files that don’t exist |
No |
read_file |
Returns a file’s lines with line numbers, in parts for long files | No |
str_replace |
Replaces one exact piece of text in an existing file (must match exactly once; never edits server.py) |
Yes (existing files only) |
delete_file |
Moves a file into .trash/ so it can be recovered; never erases it; never touches server.py |
Yes (moves to .trash/) |
git_lite |
Runs only git status, git log or git diff and returns the output |
No |
Project structure
mcp-server/
├── server.py # the MCP server and all tools
├── requirements.txt # Python dependency (mcp 1.x)
├── test_tools.py # tests that call the tools directly (no Claude needed)
├── run-server.bat # keeps the server running (restarts it if it stops)
├── run-tunnel.bat # keeps the ngrok tunnel running (restarts it if it stops)
├── start-all.bat # starts both watchdogs
├── check-status.bat # checks that both addresses respond
├── handoff/ # session handoff files (see "Handoff protocol" below)
├── .gitignore # keeps notes/, .trash/, logs/, caches and test files out of git
└── README.md
notes/ is created the first time write_note (or a saved report) writes a file. .trash/ holds files removed by delete_file. logs/ holds the watchdog output. The tests use a temporary folder and delete it afterwards.
Setup (Windows), one time
1. Install Python
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手？先看 mcpskill.org 教程 →