mcp-system-summary
Provides structured instructions to Cursor for generating comprehensive system summaries of Node.js/TypeScript codebases.
README
MCP System Summary Instructions
🔗 Live Server: https://smithery.ai/server/AliceTears/mcp-system-summary
An MCP (Model Context Protocol) server that provides structured instructions to Cursor on how to generate comprehensive system summaries for Node.js/TypeScript codebases.
Purpose: This MCP does NOT generate summaries directly. Instead, it provides detailed JSON instructions that guide Cursor through the process of:
- Inspecting and analyzing codebases
- Collecting relevant information (modules, dependencies, git history)
- Generating structured Markdown summaries with specific fields
Built with Smithery SDK
Overview
This MCP server exposes three components that help Cursor understand how to generate system summaries:
- Tool:
generate-system-summary-instructions- Returns complete JSON instructions - Prompt:
system-summary-template- Provides reusable prompt templates - Resource:
system-summary-instructions- Read-only reference documentation
Prerequisites
- Smithery API key: Get yours at smithery.ai/account/api-keys
- Node.js 20 or higher
- Cursor IDE (for using the MCP server)
Installing in Cursor
To use this MCP server in Cursor, add it to your MCP configuration:
-
Open or create the MCP configuration file:
- macOS/Linux:
~/.cursor/mcp.json - Windows:
%APPDATA%\Cursor\mcp.json
- macOS/Linux:
-
Add the following configuration to your
mcp.json:
{
"mcpServers": {
"mcp-system-summary": {
"type": "http",
"url": "https://server.smithery.ai/AliceTears/mcp-system-summary",
"headers": {}
}
}
}
-
Restart Cursor to load the MCP server.
-
Verify the installation by checking if the MCP tools are available in Cursor's MCP panel.
Configuration Options
You can configure the MCP server behavior by adding parameters to the URL or through Cursor's MCP settings:
outputDirectory: Directory path for savingcodebase_summary.md(defaults to workspace root)includeGitHistory: Whether to analyze git history (default:true)debug: Enable debug logging (default:false)
Example with configuration:
{
"mcpServers": {
"mcp-system-summary": {
"type": "http",
"url": "https://server.smithery.ai/AliceTears/mcp-system-summary?outputDirectory=./docs&includeGitHistory=true",
"headers": {}
}
}
}
Getting Started
-
Install dependencies:
npm install -
Start development server:
npm run dev -
Test the MCP components:
- Call the
generate-system-summary-instructionstool - Use the
system-summary-templateprompt - Access the
instructions://system-summaryresource
- Call the
Configuration
The server supports the following configuration options:
outputDirectory(optional): Directory path for savingcodebase_summary.md. Defaults to workspace root.includeGitHistory(optional, default:true): Whether to analyze git history for recent changes.debug(optional, default:false): Enable debug logging.
MCP Components
Tool: generate-system-summary-instructions
Returns complete JSON instructions for generating a system summary. Cursor should use these instructions to inspect the codebase and generate a comprehensive codebase_summary.md file.
Input Parameters:
outputPath(optional): Override the configured output directory
Output: JSON object containing:
- Goal and purpose
- Fields to generate (overview, status_summary, flow_summary, todo_list, key_notes)
- Required fields list
- Output file configuration
- Markdown format specifications
- Prompt templates for each field
- Notes for codebase inspection and generation process
Prompt: system-summary-template
Provides a reusable prompt template for generating system summaries with optional focus areas.
Input Parameters:
codebasePath(optional): Path to the codebase rootfocusArea(optional): Focus area (e.g., 'backend', 'frontend', 'api')
Output: Pre-formatted user message with instruction template and optional focus instructions.
Resource: system-summary-instructions
Read-only reference documentation for the system summary instruction structure.
URI: instructions://system-summary
Content: Complete instruction JSON as reference documentation for understanding the format and requirements.
Summary Fields
The instructions define the following summary fields:
- overview (required): High-level system description, technologies, and architecture
- status_summary (required): Module status, descriptions, last updated, changed files
- flow_summary (required): Main system flow and module interactions
- todo_list (optional): Pending tasks, features, and improvements
- key_notes (required): Dependencies, warnings, configuration requirements
Output Format
The generated summary is saved as codebase_summary.md in Markdown format with:
- Proper heading hierarchy (#, ##, ###)
- Tables for structured data
- Bullet points and lists
- Professional formatting suitable for users, developers, and management
Development
Your code is organized as:
src/index.ts- MCP server with tools, resources, and promptssmithery.yaml- Runtime specification
Edit src/index.ts to customize the instruction structure or add new components.
Build
npm run build
Creates bundled server in .smithery/
Deploy
Ready to deploy? Push your code to GitHub and deploy to Smithery:
-
Create a new repository at github.com/new
-
Initialize git and push to GitHub:
git add . git commit -m "Initial commit" git remote add origin https://github.com/YOUR_USERNAME/YOUR_REPO.git git push -u origin main -
Deploy your server to Smithery at smithery.ai/new
How It Works
-
Cursor calls the MCP: When a user requests a system summary, Cursor can call the tool, use the prompt, or read the resource.
-
Instructions are provided: The MCP returns structured JSON instructions that specify:
- What fields to generate
- How to inspect the codebase
- Prompt templates for each field
- Output format requirements
-
Cursor follows instructions: Cursor performs codebase inspection, collects information, and generates the summary following the provided instructions.
-
Summary is generated: Cursor creates
codebase_summary.mdwith all required fields in the specified format.
Project Structure
mcp-system-summary/
├── src/
│ └── index.ts # Main MCP server implementation
├── package.json # Dependencies and scripts
├── smithery.yaml # Runtime configuration (TypeScript)
├── README.md # This file
├── AGENTS.md # Smithery SDK guide
├── CODEBASE_SUMMARY.md # Codebase documentation
└── .gitignore # Git ignore rules
Architecture
Server Type
- Stateless Server: Creates a new instance for each request (default)
- No state is maintained between calls
Transport
- HTTP Transport: Uses HTTP/HTTPS for communication
- Hosted on Smithery infrastructure
- Accessible from anywhere via URL
Configuration Management
- Configuration is passed via URL parameters
- Each session has isolated configuration
- Supports multi-user scenarios
Dependencies
@modelcontextprotocol/sdk@^1.25.1: Core MCP SDK@smithery/sdk@^3.0.1: Smithery SDK for deploymentzod@^4: Schema validation for configuration@smithery/cli@^2.2.1: Development CLI (dev dependency)
Learn More
- Smithery Docs
- MCP Protocol
- Smithery Registry - Discover and deploy MCP servers
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。