pinecone-vector-db-mcp-server

pinecone-vector-db-mcp-server

0
knowledge_and_memorydatabases

The MCP Pinecone Vector Database Server is a project designed to manage vectorized information within a Pinecone vector database. It supports features like searching, adding, and processing vectors, particularly with Confluence and RAG-processed PDF data.

MCP Pinecone Vector Database Server

Features

  • Search for similar documents using text queries
  • Add new vectors to the database with custom metadata
  • Process and upload Confluence data in batch
  • Delete vectors by ID
  • Basic database statistics (temporarily disabled)

Prerequisites

  • Bun runtime
  • Pinecone API key
  • OpenAI API key (for generating embeddings)

Usage

Running the MCP Server

Start the server and listen for MCP commands.

Processing Confluence Data

Process and vectorize Confluence JSON data and upload vectors in batches.