Local Memory and Knowledge Base MCP server

This is a small helper program that runs on your own computer and gives your AI a memory plus a searchable knowledge base. You can save notes, add documents and web pages, and later ask questions about them. It is handy for anyone who wants their AI to remember things and look things up without sending private data to the cloud.

What this MCP server does

You ask your AI to remember something, search your notes, or answer a question. The AI uses this helper, which runs quietly on your computer. The helper saves the note, or looks through your saved notes and documents using two search methods at once (meaning-based and keyword-based), and picks the best matches. It hands the results back to your AI, which then tells you what it found or answers your question. If you have a local AI model set up, it can even write a full answer for you.

Click to zoom

What you can do with it

• Save notes and facts so your AI remembers them later
• Search your saved notes and documents with plain questions
• Add local files like text, Markdown, PDF, and Word documents to your knowledge base
• Add web pages by their link so their text is saved and searchable
• Update or delete saved memories when they change
• Ask questions and get answers based on your own documents
• Check what was saved or read, with a simple audit log

Try asking your AI

• “Remember that I prefer dark mode and short answers.”
• “Search my notes for anything about the Q3 budget.”
• “Add this web page to my knowledge base: https://example.com/article”
• “What did I save about the client meeting last week?”

What it gives back to you

You get back lists of matching notes or document snippets, short summaries, or a written answer if a local AI model is set up. In the chat, it usually looks like a few bullet points or a short paragraph with the most relevant pieces. When you save or delete something, it confirms the change. Search results include the text and where it came from.

Before you start

Who it's for

Anyone who wants a private, offline memory for their AI, especially people who work with lots of notes, documents, or research and do not want to send them to the cloud.