Local Faiss MCP

Local Faiss MCP

Local vector database server for RAG with FAISS and MCP integration

Visit Local Faiss MCP

About Local Faiss MCP

Local Faiss MCP is an open-source Model Context Protocol (MCP) server that provides local vector database functionality using FAISS for Retrieval-Augmented Generation (RAG) and AI applications. It enables users to ingest, index, and semantically search documents (TXT, PDF, MD natively; DOCX, HTML, EPUB if pandoc is installed) on their local machine, supporting persistent storage, custom Hugging Face embedding models, and two-stage retrieve and rerank workflows. The tool is suitable for developers, researchers, and teams building private, efficient RAG pipelines or seeking a self-hosted vector database solution compatible with MCP clients and agents.

Pricing Plans
Open Source (MIT License)
$0

Resources

Product Website

Visit Local Faiss MCP's official website for product details and getting started.

Visit website →

Documentation

Comprehensive guide on how to install, configure, and use Local Faiss MCP.

View docs →

Usage Examples

Explore practical examples and use cases for Local Faiss MCP to better understand its capabilities.

Read examples →

Issues and Discussions

Community forum for troubleshooting, feature requests, and discussions related to Local Faiss MCP.

Join the community →