mcp_documents_reader and paperless-mcp
These tools are **complements**: the documents reader provides local file parsing capabilities (DOCX, PDF, Excel, TXT) while the Paperless-NGX MCP server enables integration with an external document management system, allowing users to read files locally and manage them through a dedicated document server in tandem.
About mcp_documents_reader
xt765/mcp_documents_reader
Model Context Protocol (MCP) server exposes tools to read multiple document types including DOCX, PDF, Excel, and TXT. This has been tested on Trae Desktop.
Implements format-agnostic document reading via a factory pattern that auto-detects file types and routes to specialized extractors (python-docx, pypdf, openpyxl). Designed as an MCP-compliant server exposing a single `read_document` tool for AI assistants, with configuration support for Claude Desktop and Trae IDE through JSON manifests.
About paperless-mcp
nloui/paperless-mcp
An MCP (Model Context Protocol) server for interacting with a Paperless-NGX API server. This server provides tools for managing documents, tags, correspondents, and document types in your Paperless-NGX instance.
Implements comprehensive document manipulation beyond basic CRUD—including bulk operations for merging, splitting, and rotating pages, plus full-text search across indexed content. Built on the litemcp TypeScript framework with stdio transport, it integrates directly with Claude (desktop and VSCode extension) via MCP configuration, enabling AI-assisted document organization through natural language commands.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work