---
title: "Ask your AI assistant — MnemoVi! Local Video Knowledge Base"
description: "Connect your video knowledge base to the AI assistant you already use and just ask. It returns the exact moments, timecodes and on-screen details — with nothing uploaded."
canonical: https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base/use-cases/agent-mcp
locale: en
---

# Ask your AI assistant — MnemoVi! Local Video Knowledge Base

> Markdown twin of https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base/use-cases/agent-mcp
> Fetch this instead of the HTML page: same content, a fraction of the bytes.
> Site structure and the full page list for agents: https://giglabo.com/llms.txt

Connect your video knowledge base to the AI assistant you already use and just ask. It returns the exact moments, timecodes and on-screen details — with nothing uploaded.

- Type: page

## Who it is for

Power users and teams. Connect MnemoVi to the AI assistant you already use and just ask. It pulls the exact moments, timecodes and on-screen details, so your video becomes as queryable as any document.

## What you can do

- **Ask across everything** — ask "find every time we discussed X" across all of your recordings at once.
- **Get timecodes, not homework** — get a list of the exact moments on a topic without even opening the app.
- **Drop straight into a draft** — let your assistant pull quotes and on-screen details into the document you are writing.
- **Still fully local** — nothing is uploaded to make this work; your videos stay on your machine.

## How it works in practice

1. **Add or download your videos** — drop in your own files, or paste a link to pull a clip from YouTube, Instagram, TikTok or X.
2. **It reads what is said and shown** — the app picks up the words spoken and the things shown on screen: text, slides, products, prices.
3. **Search or ask — jump to the moment** — type a question, or ask your AI assistant, and land on the exact second it happened.

The connection runs over MCP, a local server MnemoVi starts on your own machine — see the [MCP server page](https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base/mcp) for the setup and the full tool list.

## A real example

You ask your assistant, "When did we promise the refund policy on camera?" It answers with the clip, the timecode and the exact words — without you opening a single file.

**Why local:** your assistant reads your videos where they live, on your computer. Nothing is sent to the cloud to answer. It runs on your own Mac or PC, with no cloud and no per-minute subscription.

## Where to go next

- [MnemoVi — Local Video Knowledge Base](https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base)
- [Connect your AI agent (MCP)](https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base/mcp)
- [Research & lectures](https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base/use-cases/research-and-lectures)

## Related

- HTML version of this page: https://giglabo.com/products/mnemoria/applications/mnemovi-local-video-knowledge-base/use-cases/agent-mcp
- Site map for agents: https://giglabo.com/llms.txt