MCP server for PDF and DOCX file reading
## Document Reader MCP Server: Universal Document Processing The **Document Reader MCP Server** provides comprehensive document reading and extraction capabilities within Google Antigravity, enabling AI-assisted processing of various document formats including Word, Excel, PowerPoint, and more. ### Why Document Reader MCP? - **Multi-Format Support**: Read Word, Excel, PowerPoint, RTF, ODT, and many other document formats - **Text Extraction**: Extract clean text content while preserving structure and formatting context - **Metadata Access**: Retrieve document metadata including author, creation date, and custom properties - **Table Extraction**: Parse tables from documents with structure preservation - **Image Extraction**: Extract embedded images and diagrams from documents ### Key Features #### 1. Document Reading ```python from anthropic import Anthropic client = Anthropic() response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Read the contract document and extract all key terms and conditions" }] ) ``` #### 2. Content Extraction ```python # Extract content response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Extract all tables from the Excel spreadsheet and convert to JSON format" }] ) ``` #### 3. Metadata Analysis ```python # Analyze metadata response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Get document metadata including author, dates, and revision history" }] ) ``` #### 4. Batch Processing ```python # Process multiple docs response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Process all documents in the folder and create a summary report" }] ) ``` ### Configuration ```json { "mcpServers": { "document-reader": { "command": "npx", "args": ["-y", "@anthropic/mcp-server-document-reader"], "env": { "DOCUMENT_MAX_SIZE": "50MB", "DOCUMENT_TEMP_DIR": "/tmp/documents" } } } } ``` ### Use Cases **Contract Analysis**: Extract and analyze contract terms from legal documents. **Data Migration**: Extract content from legacy documents for system migrations. **Report Processing**: Parse business reports and extract key metrics and data. **Document Indexing**: Extract searchable text from document archives. The Document Reader MCP Server enables comprehensive document processing, making content accessible for AI analysis and automation.
{
"mcpServers": {
"document-reader": {
"mcpServers": {
"document-reader": {
"args": [
"mcp-document-reader"
],
"command": "uvx"
}
}
}
}
}