Skip to main content
Glama

Smart Docs MCP Server

by Njengah

Smart Docs MCP Server

A production-ready Model Context Protocol (MCP) server that intelligently analyzes codebases and generates comprehensive documentation. Built with TypeScript and tree-sitter for accurate code parsing.

Features

  • Multi-Language Support: Analyze TypeScript, JavaScript, and Python codebases

  • Smart Analysis: Extract functions, classes, methods, interfaces, types, and variables

  • Documentation Coverage: Calculate documentation coverage metrics

  • Missing Doc Detection: Identify undocumented code with severity levels (critical, medium, low)

  • AI-Powered Suggestions: Generate documentation templates and improvement recommendations

  • Markdown Output: Professional documentation in markdown format

Installation

npm install npm run build

Usage

As an MCP Server

Add to your MCP client configuration (Claude Desktop):

Windows: %APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "smart-docs": { "command": "node", "args": ["C:\\ProjectFolder\\dist\\index.js"] } } }

Then restart Claude Desktop.

Available Tools

1. analyze_codebase

Analyze a codebase or file to extract code elements and calculate documentation coverage.

Input:

{ "path": "/path/to/your/codebase" }

Output:

  • Total files analyzed

  • Total code elements found

  • Documentation coverage percentage

  • Detailed breakdown by file and element

2. generate_documentation

Generate comprehensive markdown documentation for a codebase.

Input:

{ "path": "/path/to/your/codebase", "format": "markdown" }

Output:

  • Complete markdown documentation

  • Summary statistics

  • Organized by file and element type

3. detect_missing_docs

Detect code elements missing documentation with severity classification.

Input:

{ "path": "/path/to/your/codebase", "minSeverity": "critical" }

Severity Levels:

  • Critical: Public classes, interfaces, and exported functions

  • Medium: Type aliases and exported types

  • Low: Private methods and internal variables

Output:

  • List of missing documentation by severity

  • Summary statistics by severity and type

  • Detailed element information

4. suggest_improvements

Analyze existing documentation and suggest improvements.

Input:

{ "path": "/path/to/your/codebase", "limit": 20 }

Output:

  • Documentation templates for missing docs

  • Suggestions for incomplete documentation

  • Parameter and return value documentation hints

Project Structure

smart-docs-mcp/ ├── src/ │ ├── index.ts # MCP server entry point │ ├── types/ │ │ └── index.ts # TypeScript types and interfaces │ ├── parsers/ │ │ ├── base-parser.ts # Abstract parser base class │ │ ├── typescript-parser.ts # TypeScript/JavaScript parser │ │ └── python-parser.ts # Python parser │ ├── analyzers/ │ │ ├── codebase-analyzer.ts # Main analysis engine │ │ └── doc-detector.ts # Missing documentation detector │ ├── generators/ │ │ ├── markdown-generator.ts # Markdown doc generator │ │ └── improvement-suggester.ts # Improvement suggestions │ ├── tools/ │ │ ├── analyze-codebase.ts │ │ ├── generate-documentation.ts │ │ ├── detect-missing-docs.ts │ │ └── suggest-improvements.ts │ └── utils/ │ └── file-utils.ts # File system utilities ├── package.json ├── tsconfig.json └── README.md

How It Works

  1. Parsing: Uses tree-sitter to parse source code into Abstract Syntax Trees (AST)

  2. Extraction: Identifies code elements (functions, classes, etc.) from the AST

  3. Documentation Detection: Checks for JSDoc, docstrings, and inline comments

  4. Analysis: Calculates coverage and detects missing documentation

  5. Generation: Creates markdown documentation and improvement suggestions

Severity Classification

The server uses intelligent severity classification:

  • Public APIs (classes, interfaces, exported functions) → Critical

  • Type definitions and complex types → Medium

  • Private methods and internal variables → Low

Error Handling

All tools include comprehensive error handling:

  • Invalid paths return descriptive error messages

  • Unsupported file types are gracefully skipped

  • Parse errors include file location and context

Development

# Install dependencies npm install # Build the project npm run build # Watch mode for development npm run watch # Run the server npm start

Requirements

  • Node.js >= 18.0.0

  • TypeScript 5.3+

Dependencies

  • @modelcontextprotocol/sdk: MCP protocol implementation

  • tree-sitter: Code parsing engine

  • tree-sitter-typescript: TypeScript/JavaScript grammar

  • tree-sitter-python: Python grammar

  • zod: Schema validation

Testing

A test project is included in the test-project/ directory with sample files demonstrating various documentation scenarios.

License

MIT

Contributing

Contributions are welcome! Please ensure:

  • Code follows TypeScript best practices

  • All new features include error handling

  • Documentation is updated according

Deploy Server
-
security - not tested
A
license - permissive license
-
quality - not tested

local-only server

The server can only run on the client's local machine because it depends on local resources.

Enables intelligent analysis of codebases to generate comprehensive documentation, calculate documentation coverage, and identify missing documentation with severity levels. Supports TypeScript, JavaScript, and Python with AI-powered suggestions for documentation improvements.

  1. Features
    1. Installation
      1. Usage
        1. As an MCP Server
      2. Available Tools
        1. 1. analyze_codebase
        2. 2. generate_documentation
        3. 3. detect_missing_docs
        4. 4. suggest_improvements
      3. Project Structure
        1. How It Works
          1. Severity Classification
            1. Error Handling
              1. Development
                1. Requirements
                  1. Dependencies
                    1. Testing
                      1. License
                        1. Contributing

                          MCP directory API

                          We provide all the information about MCP servers via our MCP API.

                          curl -X GET 'https://glama.ai/api/mcp/v1/servers/Njengah/claude-4.5-mcp-tutorial'

                          If you have feedback or need assistance with the MCP directory API, please join our Discord server