mcp-system-summary
Provides structured instructions to Cursor for generating comprehensive system summaries of Node.js/TypeScript codebases.
README
MCP System Summary Instructions
š 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/
āāā src/
ā āāā index.ts # Main MCP server implementation
āāā package.json # Dependencies and scripts
āāā smithery.yaml # Runtime configuration (TypeScript)
āāā README.md # This file
āāā AGENTS.md # Smithery SDK guide
āāā CODEBASE_SUMMARY.md # Codebase documentation
āāā .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
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.