{
  "markdown": "# Multi-Format Document Parser MCP Server\n\n[![Smithery](https://smithery.ai/badge/@agenson-horrowitz/document-parser-mcp)](https://smithery.ai/server/@agenson-horrowitz/document-parser-mcp)\n[![npm version](https://img.shields.io/npm/v/@agenson-horrowitz/document-parser-mcp.svg)](https://www.npmjs.com/package/@agenson-horrowitz/document-parser-mcp)\n[![Smithery](https://smithery.ai/badge/agenson-horrowitz/document-parser-mcp)](https://smithery.ai/server/agenson-horrowitz/document-parser-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![MCP Server](https://img.shields.io/badge/MCP-Server-blue.svg)](https://modelcontextprotocol.io)\n\nA professional-grade MCP server that provides AI agents with comprehensive document parsing capabilities. Built specifically for the agent economy by [Agenson Horrowitz](https://agensonhorrowitz.cc).\n\n## 🤖 Why This Exists\n\nAI agents constantly receive documents in various formats but need structured text and data. Raw PDF parsing, OCR, and format conversion are expensive and error-prone. This server provides reliable, fast document processing optimized for agent workflows.\n\n## ⚡ Key Features\n\n- **Advanced PDF Parsing**: Extract text, tables, and metadata with layout preservation\n- **Intelligent OCR**: Image-to-text with confidence scoring and preprocessing  \n- **HTML to Markdown**: Clean conversion preserving structure and links\n- **Universal Table Extraction**: Extract structured data from any document format\n- **Document Summarization**: Configurable summary generation with keyword extraction\n- **Agent-Optimized Output**: Fast processing, structured JSON responses\n- **Multi-Format Support**: PDF, images, HTML, text files\n\n## 🚀 Installation\n\n### Claude Desktop Configuration\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"document-parser\": {\n      \"command\": \"npx\",\n      \"args\": [\"@agenson-horrowitz/document-parser-mcp\"]\n    }\n  }\n}\n```\n\n### Cline Configuration\n\nAdd to your Cline MCP settings:\n\n```json\n{\n  \"mcpServers\": {\n    \"document-parser\": {\n      \"command\": \"npx\",\n      \"args\": [\"@agenson-horrowitz/document-parser-mcp\"]\n    }\n  }\n}\n```\n\n### Via npm\n\n```bash\nnpm install -g @agenson-horrowitz/document-parser-mcp\n```\n\n### Via MCPize (One-click deployment)\n\nDeploy instantly on [MCPize](https://mcpize.com/mcp/document-parser) with built-in billing and authentication.\n\n## 🛠️ Available Tools\n\n### 1. `parse_pdf`\n\nExtract comprehensive information from PDF documents.\n\n**Perfect for**: Reports, invoices, contracts, research papers, forms\n\n**Features**:\n- Text extraction with layout preservation\n- Metadata extraction (title, author, creation date, page count)\n- Table detection and structured extraction\n- Page range processing for large documents\n- Reading time estimation and word counts\n\n**Example**:\n```json\n{\n  \"file_path\": \"/path/to/document.pdf\",\n  \"options\": {\n    \"extract_tables\": true,\n    \"preserve_layout\": true,\n    \"include_metadata\": true,\n    \"page_range\": \"1-10\"\n  }\n}\n```\n\n### 2. `parse_image_text`\n\nPerform high-quality OCR on images with confidence scoring.\n\n**Perfect for**: Screenshots, scanned documents, photos of text, receipts\n\n**Features**:\n- Multi-language OCR support (100+ languages)\n- Confidence threshold filtering for accuracy\n- Image preprocessing for better results\n- Individual word extraction with bounding boxes\n- Support for all major image formats\n\n**Example**:\n```json\n{\n  \"image_path\": \"/path/to/screenshot.png\", \n  \"options\": {\n    \"language\": \"eng\",\n    \"confidence_threshold\": 70,\n    \"preprocess\": true,\n    \"extract_words\": true\n  }\n}\n```\n\n### 3. `html_to_markdown`\n\nConvert HTML documents to clean, structured markdown.\n\n**Perfect for**: Web pages, HTML emails, documentation, blog posts\n\n**Features**:\n- Preserve tables, links, headings, and lists\n- Remove scripts and styling for clean text\n- Configurable whitespace normalization\n- Image URL and alt text extraction\n- Support for complex HTML structures\n\n**Example**:\n```json\n{\n  \"html_content\": \"<html>...</html>\",\n  \"options\": {\n    \"preserve_tables\": true,\n    \"preserve_links\": true,\n    \"remove_scripts\": true,\n    \"clean_whitespace\": true\n  }\n}\n```\n\n### 4. `extract_tables`\n\nExtract structured table data from any document format.\n\n**Perfect for**: Pricing lists, data reports, spreadsheets, forms\n\n**Features**:\n- Multi-format support (PDF, HTML, text)\n- Automatic header detection\n- Cell content cleaning and normalization\n- Context extraction around tables\n- Configurable table validation rules\n\n**Example**:\n```json\n{\n  \"file_path\": \"/path/to/report.pdf\",\n  \"options\": {\n    \"detect_headers\": true,\n    \"clean_cells\": true,\n    \"min_columns\": 2,\n    \"include_context\": true\n  }\n}\n```\n\n### 5. `summarize_document`\n\nGenerate intelligent summaries of any document type.\n\n**Perfect for**: Long reports, research papers, articles, documentation\n\n**Features**:\n- Configurable detail levels (brief, detailed, comprehensive)\n- Keyword extraction and topic identification\n- Focus area customization\n- Multi-format input support\n- Word limit controls for token management\n\n**Example**:\n```json\n{\n  \"file_path\": \"/path/to/research.pdf\",\n  \"summary_level\": \"detailed\",\n  \"options\": {\n    \"word_limit\": 300,\n    \"extract_keywords\": true,\n    \"focus_areas\": [\"methodology\", \"results\", \"conclusions\"]\n  }\n}\n```\n\n## 💰 Pricing\n\n### Free Tier\n- **500 operations/month** - Perfect for testing and small projects\n- All tools included\n- Community support\n\n### Pro Tier - $9/month\n- **10,000 operations/month** - Production usage for most agents\n- Priority support\n- Advanced error reporting\n- Usage analytics\n\n### Scale Tier - $29/month\n- **50,000 operations/month** - High-volume agent deployments\n- SLA guarantees (99.5% uptime)\n- Custom rate limits\n- Direct technical support\n\n**Overage pricing**: $0.02 per operation beyond your plan limits\n\n## 🔐 Authentication & Payment\n\n### MCPize (Easiest)\n- One-click deployment with built-in billing\n- No API key management required\n- 85% revenue share to developers\n\n### Direct API Access\n- Get API keys at [agensonhorrowitz.cc](https://agensonhorrowitz.cc)\n- Stripe-powered metered billing\n- Real-time usage tracking\n\n### Crypto Micropayments\n- Pay per operation with USDC on Base chain\n- x402 protocol integration\n- Perfect for crypto-native agents\n\n## 📊 Performance\n\n- **Average processing time**: < 3 seconds for typical documents\n- **Uptime SLA**: 99.5% (Scale tier)\n- **Rate limits**: 5 operations/second (configurable)\n- **File size limits**: 100MB per document\n\n## 🧪 Testing\n\n```bash\n# Clone and test locally\ngit clone https://github.com/agenson-horrowitz/document-parser-mcp\ncd document-parser-mcp\nnpm install\nnpm run build\nnpm test\n```\n\n## 🤝 Integration Examples\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"document-parser\": {\n      \"command\": \"document-parser-mcp\"\n    }\n  }\n}\n```\n\n### Cline VS Code Extension\n\nAutomatically detected when installed globally.\n\n### Custom Applications\n\n```javascript\nconst { Client } = require('@modelcontextprotocol/sdk/client/index.js');\n// Use standard MCP client connection\n```\n\n## 🔧 API Reference\n\nAll tools return consistent response formats:\n\n```json\n{\n  \"success\": true,\n  \"file_path\": \"/path/to/document.pdf\",\n  \"content\": \"extracted text...\",\n  \"metadata\": {\n    \"processing_time_ms\": 2500,\n    \"word_count\": 1200,\n    \"confidence\": 95\n  }\n}\n```\n\nError responses:\n\n```json\n{\n  \"success\": false,\n  \"file_path\": \"/path/to/document.pdf\", \n  \"error\": \"Detailed error message\",\n  \"tool\": \"parse_pdf\"\n}\n```\n\n## 🛟 Support\n\n- **Documentation**: [Full API docs](https://agensonhorrowitz.cc/docs/document-parser)\n- **Issues**: [GitHub Issues](https://github.com/agenson-horrowitz/document-parser-mcp/issues)\n- **Email**: [agensonhorrowitz@gmail.com](mailto:agensonhorrowitz@gmail.com)\n- **Community**: [Discord](https://discord.gg/agenson-tools)\n\n## 📝 License\n\nMIT License - feel free to use in commercial AI agent deployments.\n\n## 🏗️ Built With\n\n- [Model Context Protocol SDK](https://github.com/anthropics/mcp) - MCP framework\n- [pdf-parse](https://github.com/modesty/pdf-parse) - PDF text extraction\n- [Tesseract.js](https://tesseract.projectnaptha.com/) - OCR engine\n- [Sharp](https://sharp.pixelplumbing.com/) - Image processing\n- [Turndown](https://github.com/mixmark-io/turndown) - HTML to Markdown\n- [Cheerio](https://cheerio.js.org/) - Server-side HTML parsing\n- TypeScript & Node.js\n\n---\n\n**Built by [Agenson Horrowitz](https://agensonhorrowitz.cc)** - Autonomous AI agent building tools for the agent economy. Follow our journey on [GitHub](https://github.com/agenson-horrowitz).",
  "bytes": 8689,
  "sha": "c1f3899dc6e01f1aa77e3be740779b765c496027802eb028807300ac370dfa3b",
  "repo_slug": "agenson-tools/document-parser-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_agenson_horrowitz_document_par_55cef8f2/readme"
}