textrawl
Verified Safeby jeffgreendesign
Overview
Textrawl is a personal knowledge base and MCP Server that allows AI agents like Claude to search, retrieve, and add documents (emails, PDFs, notes, web pages) for enhanced contextual memory and RAG (Retrieval-Augmented Generation).
Installation
npm run devEnvironment Variables
- SUPABASE_URL
- SUPABASE_SERVICE_KEY
- OPENAI_API_KEY
- EMBEDDING_PROVIDER
- OLLAMA_BASE_URL
- OLLAMA_MODEL
- API_BEARER_TOKEN
- PORT
- LOG_LEVEL
- ALLOWED_ORIGINS
- ENABLE_MEMORY
- COMPACT_RESPONSES
Security Notes
The server employs robust security measures including `timingSafeEqual` for bearer token authentication (preventing timing attacks), rate limiting for API endpoints (protecting against DoS), and comprehensive input validation for file uploads and directory operations (preventing path traversal and content spoofing). Error handling is configured to prevent stack trace leakage in production. Database Row Level Security (RLS) is mentioned as configurable, though the application uses a service role key which bypasses RLS for its own operations, consistent with a single-tenant backend model. Child process spawning for CLI tools is done with carefully controlled arguments, mitigating injection risks. No obvious `eval` or intentional obfuscation is present.
Similar Servers
qdrant-loader
A Model Context Protocol (MCP) server that provides advanced Retrieval-Augmented Generation (RAG) capabilities to AI development tools by bridging a QDrant knowledge base for intelligent, context-aware search.
mcp-raganything
Provides a FastAPI REST API and MCP server for Retrieval Augmented Generation (RAG) capabilities, integrating with the RAG-Anything and LightRAG libraries for multi-modal document processing and knowledge graph operations.
concept-rag
Conceptual RAG system for knowledge management, providing semantic search and document analysis capabilities to AI agents over a private document library, enriched with WordNet data.
the-pensieve
The Pensieve server acts as a RAG-based knowledge management system, allowing users to store, query, and analyze their knowledge using natural language and LLM-powered insights.