Softority MCP Server
Provides AI clients with safe, structured access to local filesystem, Git repositories, and project contexts, featuring file operations, git status/diff, project management, and built-in code review/bug analysis prompts.
README
Softority MCP Server
A modular, high-performance Model Context Protocol (MCP) server providing AI clients (like Claude Desktop, Cursor, and Windsurf) with safe, structured access to your local filesystem, Git repositories, and project contexts.
🚀 Features
- File Operations (
file): Read files, list directory contents, search codebase (ripgrepstyle), and inspect project tree representations. - Git Integration (
git): Inspect real-timegit statusandgit diffworking tree changes. - Project Management (
project): Register local projects, track project metadata using a local SQLite database, and run automated AI analysis prompts. - Built-in AI Prompts: Prompts for automated
code_reviewandbug_analysis.
📦 Installation Options
Choose the installation method that best suits your needs:
Option 1: Automatic One-Line Installer (Recommended for Users)
Automated scripts download the latest pre-built release, set up dependencies, create a binary wrapper, and configure your system PATH.
Windows (PowerShell):
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/prashantkumar342/code-with-softority/main/scripts/installers/install.ps1" -OutFile "$env:TEMP\install.ps1"; & "$env:TEMP\install.ps1"
macOS / Linux (Bash):
curl -fsSL "https://raw.githubusercontent.com/prashantkumar342/code-with-softority/main/scripts/installers/install.sh" | bash
After installation, the global command code-with-softority will be available in your terminal!
Option 2: Pre-built Release Package (No Compilation Required)
If you prefer not to use installer scripts, you can download the standalone pre-built directory from GitHub Releases:
- Go to Releases on GitHub and download
release.zip. - Extract
release.zipto your preferred directory (e.g.,~/.code-with-softority). - Open a terminal in the extracted folder and run:
npm install --production - Point your MCP client to the bundled executable at
./build/server.js.
Option 3: Build from Source (For Developers & Contributors)
If you want to modify or contribute to the source code:
- Clone the repository:
git clone https://github.com/prashantkumar342/code-with-softority.git cd mcp-server - Install dependencies:
npm install - Environment Setup:
cp .env.example .env - Initialize Database:
npx prisma generate npx prisma db push - Build the server:
This compiles the server into a single-file executable atnpm run buildbuild/server.js.
⚙️ MCP Client Configuration
Claude Desktop Setup
Edit your claude_desktop_config.json:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Add the server configuration:
{
"mcpServers": {
"softority": {
"command": "code-with-softority",
"args": []
}
}
}
(If installed manually or built from source, replace "command": "code-with-softority" with "command": "node" and "args": ["/absolute/path/to/build/server.js"])
📂 Directory Structure
mcp/
├── build/ # Pre-compiled bundled executable (build/server.js)
├── scripts/ # Installer scripts for Windows & Unix
│ └── installers/ # install.ps1, install.sh, and setup guides
├── prisma/ # Prisma schema & SQLite database migrations
├── tests/ # Vitest unit and integration test suite
└── src/ # Source code
├── server.ts # MCP Server entry point
├── core/ # Registries (Tools, Resources, Prompts, Database)
└── modules/ # Feature domain modules
├── file/ # File tools & resources
├── git/ # Git status & diff tools
└── project/ # Project registration & prompt analysis
🧪 Testing & Verification
Run the full Vitest suite:
npm run test
📄 License
This project is licensed under a custom Source-Available & Collaboration License. See LICENSE for full details.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。