Style-Coach-MCP
Provides data-driven cover letter coaching by analyzing tone, keywords, and structure using a database of successful examples and corporate strategy reports.
README
Style-Coach-MCP
An advanced cover letter coaching tool powered by data-driven analysis. It helps users improve their job applications by analyzing tone, keywords, and structure based on 19,000+ successful cover letter examples and corporate strategy reports.
Features
-
Success DNA Injection Analyzes job-specific successful cover letters to extract high-frequency keywords. If you apply for a 'Marketing' role, it checks if you used industry-standard terms found in successful applications.
-
Strategy Report Integration (Dual Mode) Checks if your text aligns with both the Company's Core Values (Organization) and the Job's Key Competencies (Role). It loads strategy documents to provide context-aware feedback.
-
Cliche Cleaner Detects and warns about overused, vague expressions like "I will work hard" or "learning attitude" that recruiters often dislike.
-
Power Word Injector Identifies passive or weak verbs (e.g., "did", "participated") and suggests strong, active alternatives (e.g., "spearheaded", "achieved", "optimized") to enhance professionalism.
-
Readability Check Enforces structural rules for better readability, such as keeping sentences under 80 characters and ensuring the first sentence contains key results (Head-first structure).
Performance Optimization
This MCP uses a Pre-computation Strategy to ensure high performance. Instead of parsing thousands of data files at runtime, it processes raw data during the build phase into a lightweight JSON cache.
- Server Startup: < 100ms
- Memory Usage: Optimized (Loads only essential keyword maps)
Installation & Setup
- Prerequisites
- Node.js (v16 or higher)
- Data files (JSON/DOCX) placed in the designated data directory (see Data Privacy).
-
Install Dependencies npm install
-
Build (Includes Pre-computation) npm run build
This command runs the pre-processing script to generate 'dist/data_cache.json' and then compiles the TypeScript code.
- Configure Claude Desktop Add the following to your claude_desktop_config.json:
{ "mcpServers": { "style-coach": { "command": "node", "args": [ "C:\Users\jyokm\OneDrive\Desktop\coverletter\Style-Coach-MCP\dist\index.js" ] } } }
Usage
Ask Claude to analyze your cover letter:
"Here is my cover letter for a Marketing role at CJ CheilJedang. Please analyze it using Style Coach."
Claude will call the 'coach_cover_letter' tool with the text, role ('Marketing'), and organization ('CJ CheilJedang').
Data Privacy Notice
This repository contains only the Logic and Code. Actual training data (19,000+ cover letters) and corporate strategy reports are NOT included due to privacy and copyright reasons.
To use your own data:
- Set the 'COVERLETTER_DATA_DIR' environment variable to your data path.
- Ensure your data follows the expected structure (JSON array for cover letters, DOCX/MD for strategies).
- Run 'npm run build' to generate the cache.
License
ISC
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.