Skip to main content
Glama
vedantparmar12

Document Automation MCP Server

by vedantparmar12
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

šŸ“š Document Automation MCP Server

Python MCP License Code Style

A powerful Model Context Protocol (MCP) server that provides intelligent codebase analysis, comprehensive documentation generation, and multi-format export capabilities. Built for seamless integration with Claude and other AI assistants.

āœØ Features

šŸ” Intelligent Codebase Analysis

  • AST Parsing: Deep analysis of Python and JavaScript code structures

  • Framework Detection: Automatically identifies frameworks (React, Flask, Django, FastAPI, etc.)

  • Database Schema Analysis: Extracts and visualizes database relationships

  • API Endpoint Discovery: Maps REST endpoints with methods and parameters

  • Security Scanning: Identifies potential vulnerabilities and best practices

  • Dependency Tracking: Analyzes project dependencies and versions

šŸ“ Professional Documentation Generation

  • Multiple Formats: Markdown, HTML, PDF, DOCX, Confluence, Notion, JSON, EPUB

  • Interactive Documentation: Search, navigation, syntax highlighting

  • Mermaid Diagrams: Architecture, database ER, API flows, dependency graphs

  • Multi-language Support: Built-in internationalization

  • Custom Themes: Modern, minimal, dark, corporate, and more

  • Accessibility Compliant: WCAG 2.1 AA standards

šŸš€ Advanced Capabilities

  • Pagination Support: Handles large repositories efficiently

  • Background Processing: Async analysis for better performance

  • Smart Chunking: Token-aware content splitting

  • Concurrent Analysis: Parallel file processing

  • Export Automation: Batch export to multiple formats

  • Archive Generation: ZIP, TAR, TAR.GZ support

Related MCP server: JSON Resume MCP Server

šŸ“‹ Table of Contents

šŸš€ Installation

Prerequisites

  • Python 3.8 or higher

  • Git

  • Claude Desktop or MCP-compatible client

Using pip

# Clone the repository git clone https://github.com/vedantparmar12/Document-Automation.git cd Document-Automation # Install dependencies pip install -r requirements.txt

Using uv (Recommended)

# Install uv (if not already installed) pip install uv # Install dependencies with uv uv pip install -r requirements.txt

šŸŽÆ Quick Start

1. Configure Claude Desktop

Add the following to your Claude Desktop configuration file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{ "mcpServers": { "document-automation": { "command": "python", "args": [ "C:\\path\\to\\Document-Automation\\run_server.py" ] } } }

2. Start the Server

# Using Python directly python run_server.py # Or using uv uv run python run_server.py

3. Use in Claude

Once configured, Claude can analyze codebases and generate documentation:

Analyze this repository: https://github.com/username/repo Generate comprehensive documentation in HTML format

āš™ļø Configuration

Environment Variables

Create a .env file in the project root:

# Analysis Settings MAX_FILES=1000 MAX_TOKENS_PER_CHUNK=4000 PAGINATION_STRATEGY=auto # Security Settings ENABLE_SECURITY_SCAN=true CONTENT_FILTERING=true # Export Settings DEFAULT_OUTPUT_DIR=./docs DEFAULT_THEME=modern ENABLE_DIAGRAMS=true

MCP Server Configuration

The server can be configured via wrangler.toml for Cloudflare Workers deployment:

name = "document-automation" compatibility_date = "2024-01-01" [env.production] vars = { ENVIRONMENT = "production" }

šŸ“– Usage Examples

Analyze a Local Codebase

from src.tools.consolidated_documentation_tools import analyze_codebase result = analyze_codebase( path="/path/to/project", source_type="local", include_ast_analysis=True, include_mermaid_diagrams=True, include_security_analysis=True ) print(f"Analysis ID: {result['analysis_id']}") print(f"Total Files: {result['metrics']['total_files']}") print(f"Frameworks: {result['technology_stack']['primary_technologies']}")

Analyze a GitHub Repository

result = analyze_codebase( path="https://github.com/username/repo.git", source_type="github", include_api_endpoints=True, include_database_analysis=True )

Generate Documentation

from src.tools.consolidated_documentation_tools import generate_documentation docs = generate_documentation( analysis_id="analysis_20241212_123456_789", format="interactive", theme="modern", include_toc=True, include_search=True, auto_export_formats=["pdf", "html", "markdown"] ) print(f"Documentation generated: {docs['generated_files']}")

Export to Multiple Formats

from src.tools.consolidated_documentation_tools import export_documentation exports = export_documentation( analysis_id="analysis_20241212_123456_789", formats=["html", "pdf", "docx", "markdown"], theme="corporate", include_diagrams=True, accessibility_compliance=True, archive_formats=["zip"] ) print(f"Exported {len(exports['exported_files'])} files")

šŸ”Œ API Reference

Core Tools

analyze_codebase

Comprehensive codebase analysis with built-in features.

Parameters:

  • path (str): Local path or GitHub URL

  • source_type (str): "local" or "github"

  • include_ast_analysis (bool): Enable AST parsing

  • include_framework_detection (bool): Detect frameworks

  • include_database_analysis (bool): Analyze database schemas

  • include_mermaid_diagrams (bool): Generate diagrams

  • include_api_endpoints (bool): Extract API routes

  • include_security_analysis (bool): Security scanning

  • max_files (int): Maximum files to analyze (default: 1000)

  • pagination_strategy (str): "auto", "file_by_file", "chunk_by_chunk", "smart"

Returns:

{ "success": bool, "analysis_id": str, "comprehensive_analysis": { "project_structure": {...}, "dependencies": [...], "api_endpoints": [...], "mermaid_diagrams": {...}, "security_analysis": {...} }, "metrics": {...} }

generate_documentation

Generate professional documentation with all features built-in.

Parameters:

  • analysis_id (str): ID from previous analysis

  • format (str): "markdown", "html", "pdf", "interactive", etc.

  • theme (str): "modern", "minimal", "dark", "corporate", etc.

  • include_toc (bool): Table of contents

  • include_search (bool): Search functionality

  • include_navigation (bool): Navigation sidebar

  • auto_export_formats (list): Additional export formats

Returns:

{ "success": bool, "generated_files": [...], "documentation_stats": {...} }

export_documentation

Export to multiple formats with advanced features.

Parameters:

  • analysis_id (str): ID from previous analysis

  • formats (list): Export formats

  • theme (str): Documentation theme

  • accessibility_compliance (bool): WCAG 2.1 AA compliance

  • archive_formats (list): Archive types ["zip", "tar", "tar.gz"]

šŸ“ Project Structure

Document-Automation/ ā”œā”€ā”€ src/ ā”‚ ā”œā”€ā”€ analyzers/ # Codebase analysis modules ā”‚ ā”‚ ā”œā”€ā”€ base_analyzer.py ā”‚ ā”‚ ā”œā”€ā”€ codebase_analyzer.py ā”‚ ā”‚ ā”œā”€ā”€ database_analyzer.py ā”‚ ā”‚ ā”œā”€ā”€ framework_detector.py ā”‚ ā”‚ ā””ā”€ā”€ project_classifier.py ā”‚ ā”œā”€ā”€ diagrams/ # Diagram generation ā”‚ ā”‚ ā”œā”€ā”€ architecture_diagrams.py ā”‚ ā”‚ ā”œā”€ā”€ database_diagrams.py ā”‚ ā”‚ ā””ā”€ā”€ mermaid_generator.py ā”‚ ā”œā”€ā”€ export/ # Format exporters ā”‚ ā”‚ ā””ā”€ā”€ format_exporter.py ā”‚ ā”œā”€ā”€ generators/ # Documentation generators ā”‚ ā”‚ ā”œā”€ā”€ documentation_generator.py ā”‚ ā”‚ ā”œā”€ā”€ interactive_doc_generator.py ā”‚ ā”‚ ā”œā”€ā”€ professional_doc_generator.py ā”‚ ā”‚ ā””ā”€ā”€ readme_template.py ā”‚ ā”œā”€ā”€ pagination/ # Pagination and chunking ā”‚ ā”‚ ā”œā”€ā”€ chunker.py ā”‚ ā”‚ ā”œā”€ā”€ context.py ā”‚ ā”‚ ā”œā”€ā”€ strategies.py ā”‚ ā”‚ ā””ā”€ā”€ token_estimator.py ā”‚ ā”œā”€ā”€ parsers/ # Language parsers ā”‚ ā”‚ ā”œā”€ā”€ ast_analyzer.py ā”‚ ā”‚ ā”œā”€ā”€ javascript_parser.py ā”‚ ā”‚ ā”œā”€ā”€ python_parser.py ā”‚ ā”‚ ā””ā”€ā”€ mcp_analyzer.py ā”‚ ā”œā”€ā”€ processing/ # Background processing ā”‚ ā”‚ ā”œā”€ā”€ background_processor.py ā”‚ ā”‚ ā””ā”€ā”€ concurrent_analyzer.py ā”‚ ā”œā”€ā”€ security/ # Security features ā”‚ ā”‚ ā”œā”€ā”€ content_filter.py ā”‚ ā”‚ ā””ā”€ā”€ validation.py ā”‚ ā”œā”€ā”€ tools/ # MCP tools ā”‚ ā”‚ ā””ā”€ā”€ consolidated_documentation_tools.py ā”‚ ā”œā”€ā”€ schemas.py # Data schemas ā”‚ ā””ā”€ā”€ server.py # MCP server ā”œā”€ā”€ run_server.py # Server entry point ā”œā”€ā”€ requirements.txt # Python dependencies ā”œā”€ā”€ pyproject.toml # Project metadata ā””ā”€ā”€ README.md # This file

šŸ—ļø Architecture

System Overview

flowchart TB Client[Claude/MCP Client] --> Server[MCP Server] Server --> Analyzer[Codebase Analyzer] Server --> Generator[Doc Generator] Server --> Exporter[Format Exporter] Analyzer --> AST[AST Parser] Analyzer --> Framework[Framework Detector] Analyzer --> Database[DB Analyzer] Analyzer --> Security[Security Scanner] Generator --> Interactive[Interactive HTML] Generator --> Professional[Professional Docs] Generator --> Diagrams[Mermaid Diagrams] Exporter --> PDF[PDF Export] Exporter --> HTML[HTML Export] Exporter --> Markdown[Markdown Export] Exporter --> DOCX[DOCX Export]

Component Interaction

sequenceDiagram participant Client participant Server participant Analyzer participant Generator participant Exporter Client->>Server: analyze_codebase() Server->>Analyzer: Parse & Analyze Analyzer->>Analyzer: AST, Framework, DB, Security Analyzer-->>Server: Analysis Results Server-->>Client: analysis_id Client->>Server: generate_documentation() Server->>Generator: Create Docs Generator->>Generator: Format, Theme, Diagrams Generator-->>Server: Documentation Server-->>Client: Generated Files Client->>Server: export_documentation() Server->>Exporter: Convert Formats Exporter->>Exporter: PDF, HTML, DOCX Exporter-->>Server: Exported Files Server-->>Client: Export Results

šŸ› ļø Development

Setup Development Environment

# Create virtual environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate # Install dev dependencies pip install -r requirements.txt pip install black pytest pytest-cov mypy # Run tests pytest tests/ # Format code black src/ # Type checking mypy src/

Running Tests

# Run all tests pytest # Run with coverage pytest --cov=src --cov-report=html # Run specific test file pytest tests/test_analyzer.py

Code Quality

# Format with Black black src/ tests/ # Lint with Flake8 flake8 src/ tests/ # Type check with MyPy mypy src/

šŸ¤ Contributing

Contributions are welcome! Please follow these guidelines:

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature/amazing-feature

  3. Commit your changes: git commit -m 'Add amazing feature'

  4. Push to the branch: git push origin feature/amazing-feature

  5. Open a Pull Request

Contribution Guidelines

  • Follow PEP 8 style guide

  • Add tests for new features

  • Update documentation

  • Ensure all tests pass

  • Keep commits atomic and well-described

šŸ“Š Performance

Benchmarks

Operation

Small Repo (<100 files)

Medium Repo (100-1000 files)

Large Repo (>1000 files)

Analysis

~5 seconds

~30 seconds

~2-5 minutes

Doc Generation

~2 seconds

~10 seconds

~30 seconds

Export (all formats)

~3 seconds

~15 seconds

~45 seconds

Optimization Tips

  • Use pagination_strategy="smart" for large repositories

  • Enable include_security_analysis=False if not needed

  • Limit max_files for faster analysis

  • Use concurrent processing for multiple projects

šŸ› Troubleshooting

Common Issues

Issue: ModuleNotFoundError: No module named 'src'

# Solution: Add project root to PYTHONPATH export PYTHONPATH="${PYTHONPATH}:/path/to/Document-Automation"

Issue: GitHub rate limiting

# Solution: Set GitHub token export GITHUB_TOKEN="your_token_here"

Issue: Memory errors with large repositories

# Solution: Use pagination analyze_codebase(path="...", max_files=500, pagination_strategy="smart")

šŸ“„ License

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

šŸ™ Acknowledgments

šŸ“® Contact

Vedant Parmar - @vedantparmar12

Project Link: https://github.com/vedantparmar12/Document-Automation

šŸ—ŗļø Roadmap

  • Support for more programming languages (Go, Rust, Java)

  • Real-time collaboration features

  • Cloud storage integration (S3, GCS)

  • API documentation auto-generation from OpenAPI specs

  • Enhanced security scanning with CVE database

  • Performance profiling and optimization suggestions

  • Custom template support

  • CLI tool for standalone use

ā­ Star History

If you find this project useful, please consider giving it a star! ā­

Made with ā¤ļø by Vedant Parmar

This server cannot be installed

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

How are these scores calculated?

Resources

Appeared in Searches

New MCP Servers

Latest Blog Posts

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/vedantparmar12/Document-Automation'

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