MCP Pinecone Vector Database Server

what is MCP Pinecone Vector Database Server?

MCP Pinecone Vector Database Server is a server that implements a Model Context Protocol (MCP) for reading and writing vectorized information to a Pinecone vector database, designed to work with RAG-processed PDF data and Confluence data.

how to use MCP Pinecone Vector Database Server?

To use the server, clone the repository, install dependencies, set up your environment variables, and run the server using the Bun runtime. You can also test it with an example client.

key features of MCP Pinecone Vector Database Server?

• 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)

use cases of MCP Pinecone Vector Database Server?

1. Searching for similar documents in a vector database.
2. Adding and managing vectorized data for machine learning applications.
3. Processing and vectorizing Confluence documentation for better searchability.

FAQ from MCP Pinecone Vector Database Server?

• What are the prerequisites for running the server?

You need the Bun runtime, a Pinecone API key, and an OpenAI API key for generating embeddings.

• How do I add new vectors to the database?

Use the add-vector tool with the required parameters to add a document to the database.

• Can I delete vectors from the database?

Yes, you can delete vectors by their ID using the delete-vectors tool.