MCP ContentEngineering - Simplified

License: MIT Node.js Version TypeScript Jest MCP Protocol Claude Desktop Cursor IDE Maintenance

A simplified Model Context Protocol (MCP) server for raw Markdown content access. This server provides a single powerful tool for accessing raw Markdown files or combining multiple files from directories without any processing or parsing.

🚀 Quick Start

Prerequisites

Node.js 18+ and npm
Markdown files or directories containing .md files
MCP-compatible client (like Claude Desktop, Cursor IDE, or any MCP client)

Installation & Configuration

Option 1: Using npx from GitHub (Recommended)

No installation needed! Just configure your MCP client:

For Claude Desktop (

{ "mcpServers": { "mcp-content-engineering": { "command": "npx", "args": ["-y", "hendrickcastro/MCPContentEngineering"], "env": { "CONTENT_SOURCE_TYPE": "file", "CONTENT_SOURCE_PATH": "/path/to/your/business-rules.md" } } } }

For Cursor IDE:

{ "mcpServers": { "mcp-content-engineering": { "command": "npx", "args": ["-y", "hendrickcastro/MCPContentEngineering"], "env": { "CONTENT_SOURCE_TYPE": "directory", "CONTENT_SOURCE_PATH": "/path/to/your/docs/" } } } }

Option 2: Local Development Installation

Clone and setup:

git clone https://github.com/hendrickcastro/MCPContentEngineering.git cd MCPContentEngineering npm install npm run build

Configure content source: Create a .env file with your content configuration:

# For single file CONTENT_SOURCE_TYPE=file CONTENT_SOURCE_PATH=/docs/architecture-guide.md # For directory with multiple .md files CONTENT_SOURCE_TYPE=directory CONTENT_SOURCE_PATH=/docs/knowledge-base/

Configure MCP client with local path:

{ "mcpServers": { "mcp-content-engineering": { "command": "node", "args": ["path/to/MCPContentEngineering/dist/server.js"] } } }

🛠️ Available Tool

MCPContentEngineering provides 1 specialized tool for Markdown content access:

🔄 Raw Content Access - `content_get_raw`

Get raw Markdown content without any processing, parsing, or indexing. Perfect for accessing business rules, documentation, or knowledge bases exactly as they are written.

Features:

✅ Single File Mode: Returns exact file content
✅ Directory Mode: Combines ALL .md files with clear separators
✅ Recursive Search: Finds .md files in subdirectories
✅ No Processing: Content returned exactly as written
✅ Metadata Included: File size, modification date, source info

🔧 Configuration Types & Examples

MCPContentEngineering supports two content source types with simple configuration:

📋 Environment Variables

Variable

Description

Values

Required

CONTENT_SOURCE_TYPE

Content source type

file

directory

Yes

CONTENT_SOURCE_PATH

Path to file or directory

Absolute or relative path

Yes

🔧 Configuration Examples

1. 📄 Single Business Rules File

Perfect for accessing a specific rules or documentation file:

2. 📁 Knowledge Base Directory

Combines all Markdown files from a documentation directory:

3. 🏗️ Architecture Documentation

Access comprehensive architecture documentation:

4. 📐 Project Standards & Patterns

Access coding standards and design patterns:

5. 🔄 Local Development Configuration

For local development and testing:

{ "mcpServers": { "mcp-content-engineering": { "command": "node", "args": ["./MCPContentEngineering/dist/server.js"], "env": { "CONTENT_SOURCE_TYPE": "directory", "CONTENT_SOURCE_PATH": "./docs" } } } }

📋 Usage Examples

Single File Access

// Returns exact content of business-rules.md const result = await content_get_raw({}); console.log(result.data.content); // Output: Raw markdown content exactly as written // "# Business Rules\n\n## Validation Rules\n..." console.log(result.data.source_info); // Output: "Single file: /docs/business-rules.md" console.log(result.data.total_files); // Output: 1

Directory Combination

// Combines all .md files from directory const result = await content_get_raw({}); console.log(result.data.content); // Output: Combined content with separators: /*  # Business Rules ...  # Design Patterns ... */ console.log(result.data.source_info); // Output: "Combined 2 .md files from: /docs/" console.log(result.data.total_files); // Output: 2

Response Structure

interface ContentResponse { content: string; // Raw markdown content source_info: string; // Source description total_files: number; // Number of files processed size_bytes: number; // Total content size last_modified: string; // ISO timestamp of latest modification }

💡 Use Cases

1. 📚 Enterprise Knowledge Base

Access company documentation, policies, and procedures:

{ "CONTENT_SOURCE_TYPE": "directory", "CONTENT_SOURCE_PATH": "/company/knowledge-base/" }

2. 🏗️ Architecture Documentation

Provide AI models with architectural guidelines and patterns:

{ "CONTENT_SOURCE_TYPE": "file", "CONTENT_SOURCE_PATH": "/docs/architecture-layers-summary.md" }

3. 📐 Coding Standards

Access development standards and best practices:

{ "CONTENT_SOURCE_TYPE": "directory", "CONTENT_SOURCE_PATH": "/standards/" }

4. 🔍 Business Rules Engine

Provide specific business rules for decision-making:

{ "CONTENT_SOURCE_TYPE": "file", "CONTENT_SOURCE_PATH": "/rules/validation-rules.md" }

5. 📖 Project Documentation

Combine all project documentation for comprehensive context:

{ "CONTENT_SOURCE_TYPE": "directory", "CONTENT_SOURCE_PATH": "/project/docs/" }

🚨 Troubleshooting Common Issues

File/Directory Not Found

Issue: File not found or Directory not found
Solution: Verify the path exists and is accessible
Check: Use absolute paths for clarity

No .md Files Found

Issue: No .md files found in directory
Solution: Ensure directory contains .md files
Note: Searches recursively in subdirectories

Permission Errors

Issue: Permission denied when accessing files
Solution: Ensure read permissions on files/directories
Check: File ownership and access rights

Configuration Issues

Issue: CONTENT_SOURCE_PATH not configured
Solution: Set both required environment variables
Required: CONTENT_SOURCE_TYPE and CONTENT_SOURCE_PATH

🧪 Testing

Run the comprehensive test suite:

npm test

The test suite includes:

✅ Unit Tests: Temporary file testing with various scenarios
✅ Real Tests: Actual architecture documentation testing
✅ Error Handling: Comprehensive error case coverage
✅ Content Validation: JSON serialization and data structure validation

Test Results:

Test Suites: 2 passed, 2 total Tests: 11 passed, 11 total

🏗️ Architecture

Project Structure

MCPContentEngineering/ ├── src/ │ ├── __tests__/ # Comprehensive test suite │ │ ├── unit.test.ts # Unit tests with temp files │ │ └── real.test.ts # Real file testing │ ├── tools/ # Tool implementation │ │ ├── contentOperations.ts # Single tool: content_get_raw │ │ ├── types.ts # Type definitions │ │ └── index.ts # Tool exports │ ├── server.ts # MCP server setup │ ├── tools.ts # Tool definitions and schemas │ └── mcp-server.ts # Tool re-exports ├── dist/ # Compiled JavaScript output └── package.json # Dependencies and scripts

Key Features

⚡ Zero Processing: Content returned exactly as written
📁 Recursive Search: Finds .md files in all subdirectories
🔄 File Combination: Intelligent merging with clear separators
📊 Rich Metadata: Comprehensive file and content information
🛡️ Error Handling: Robust error handling and validation
🔧 Simple Configuration: Just two environment variables

📝 Important Notes

File Types: Only processes .md (Markdown) files
Content Preservation: Returns content exactly as written - no processing
Directory Mode: Recursively finds ALL .md files in subdirectories
File Separators: Clear HTML comment separators when combining files
Encoding: Assumes UTF-8 encoding for all files
Security: Read-only operations only - no file modifications

🤝 Contributing

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Make your changes and add tests
Ensure all tests pass (npm test)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Built with the Model Context Protocol SDK
Uses fs-extra for file operations
Uses glob for file discovery
Comprehensive testing with Jest

🏷️ Tags & Keywords

Content Management: markdown documentation knowledge-base content-access raw-content file-processing text-processing document-management

MCP & AI: model-context-protocol mcp-server mcp-tools ai-tools claude-desktop cursor-ide anthropic llm-integration ai-content intelligent-content

Technology: typescript nodejs npm-package cli-tool file-system markdown-reader content-sdk text-api file-api content-connector

Use Cases: business-rules architecture-docs coding-standards project-docs knowledge-management content-retrieval documentation-access standards-access rule-engine content-automation

🎯 MCPContentEngineering provides simple, direct access to raw Markdown content through the Model Context Protocol. Perfect for AI models that need access to business rules, documentation, or knowledge bases without any processing overhead! 🚀

Deploy Server

HTTP connection URL

security – no known vulnerabilities

license - not tested

quality - confirmed to work

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Tools

content_get_raw

Enables direct access to raw Markdown content from files or directories without processing. Perfect for providing AI models with business rules, documentation, or knowledge bases exactly as written.

Related MCP Servers

Markdownify MCP Server
zcaceres
A
security
-
license
A
quality
Converts various file types and web content to Markdown format. It provides a set of tools to transform PDFs, images, audio files, web pages, and more into easily readable and shareable Markdown text.
Last updated -
10
7
2,163
MIT License
MarkItDown MCP
xkiranj
-
security
-
license
-
quality
Converts various file types (documents, images, audio, web content) to markdown format without requiring Docker, supporting PDF, Word, Excel, PowerPoint, images, audio files, web URLs, and more.
Last updated -
222
9
read-website-fast
just-every
A
security
-
license
A
quality
Fast, token-efficient web content extraction tool that converts websites to clean Markdown for AI agents, featuring smart caching, content extraction with Mozilla Readability, and polite crawling capabilities.
Last updated -
1
148
91
MIT License
markdownlint-mcp
ernestgwilsonii
-
security
-
license
-
quality
Provides AI assistants with the ability to lint, validate, and auto-fix Markdown files to ensure compliance with established Markdown standards and best practices.
Last updated -
1
MIT License

View all related MCP servers