Knowledge MCP Server

A Model Context Protocol (MCP) server that provides tools for managing and querying knowledge bases through vector databases. This server is built on top of the dynamic-mcp-server framework.

Overview

The Knowledge MCP Server provides a set of tools that allow AI models to create, manage, and query knowledge sources using vector databases. It enables semantic search capabilities and dynamic tool generation for specific knowledge domains.

Features

- Vector database integration for storing and querying embeddings
- Document processing pipeline for content ingestion
- Text chunking and embedding generation
- Dynamic tool registration and management
- Secure access control for knowledge sources
- Support for website crawling and content extraction
- MongoDB integration for metadata and vector storage

Prerequisites

- Node.js 18 or later
- MongoDB Atlas M10 or higher instance (for vector search capabilities)
- OpenAI API key

Installation

1. Clone the repository:

   git clone https://github.com/your-org/knowledge-mcp-server.git
   cd knowledge-mcp-server
   

2. Install dependencies:

   npm install
   

Configuration

Create a .env file in the project root with the following variables:

```env