MCP-RAG is a low-latency retrieval-augmented generation service providing intelligent knowledge management through a modular MCP protocol architecture.

Core Capabilities:

Knowledge Management

• Add text content manually (facts, definitions, notes, conversation summaries)

• Process 25+ document formats (PDF, DOCX, PPTX, XLSX, TXT, HTML, CSV, JSON, XML, ODT, ODP, ODS, RTF, images with OCR, emails) using advanced semantic chunking with structure preservation, automatic denoising, and metadata extraction

• Get comprehensive statistics on document counts, file type distribution, processing methods, and structural complexity

Intelligent Retrieval

• Query the knowledge base with semantic search (<100ms latency)

• Use Raw mode for direct retrieval or Summary mode for LLM-powered intelligent summarization

• Apply filters for targeted search by file type, document structure (tables, titles), or processing method

Performance Optimization

• Monitor and optimize vector database performance with health diagnostics

• Reindex with optimized profiles (small/medium/large/auto)

• Manage embedding cache with performance monitoring (hit rates, memory usage) and cache clearing

Technical Features

• Multi-provider support (Doubao, Ollama for LLMs; Doubao API and local sentence-transformers for embeddings)

• Web interface for configuration management, document management, and API documentation (Swagger UI)

• HTTP API and MCP protocol support

Enables local AI model inference for RAG operations, allowing private document processing and knowledge base interactions without sending data to external services.

Provides RAG (Retrieval-Augmented Generation) capabilities using OpenAI's language models and embedding models for intelligent document processing, semantic search, and knowledge base question answering.