PyVector MCP Server

Example Use Cases

• 1

  Fast and efficient similarity search on local vector databases.

• 2

  Integrate vector search capabilities with local LLMs via MCP protocol.

• 3

  A lightweight, dependency-minimal vector database with fallback support.

Description

PyVector is a lightweight vector database implementation with Model Context Protocol (MCP) server support, designed to enable fast similarity search and text embedding generation for local large language model (LLM) applications. It supports multiple index types, persistent storage, and metadata, while gracefully handling missing optional dependencies with fallback implementations. The MCP server integration allows seamless use as a tool for LLMs, and it also offers an HTTP server for easy local integration.