TODAY'S ISSUE
TODAY’S DAILY DOSE OF DATA SCIENCE
Build an MCP-powered RAG over Videos
Today, we are building an MCP-driven video RAG that ingests a video and lets you chat with it.
It also fetches the exact video chunk where an event occurred.
Our tech stack:
- ​Ragie​ for video ingestion and retrieval.
- Cursor as the MCP host.
Here's the workflow:
- User specifies video files and a query.
- An Ingestion tool indexes the videos in Ragie.
- A Query tool retrieves info from Ragie Index with citations.
- A show-video tool returns the video chunk that answers the query.
Here's the MCP-powered video rag in action:
Implementation details
​MCP-powered RAG over videos​​
Let's implement this (the code is linked later in the issue)!
Ingest data
We implement a method to ingest video files into the Ragie index.
We also specify the audio-video mode to load both audio and video channels during ingestion.
Retrieve data
We retrieve the relevant chunks from the video based on the user query.
Each chunk has a start time, an end time, and a few more details that correspond to the video segment.
Create MCP Server
We integrate our RAG pipeline into an MCP server with 3 tools:
ingest_data_tool: Ingests data into Ragie index.retrieve_data_tool: Retrieves data based on the user query.show_video_tool: Creates video chunks from the original video.
Integrate MCP server with Cursor
To integrate the MCP server with Cursor, go to Settings → MCP → Add new global MCP server.
In the JSON file, add what's shown below:
Done!
Your local Ragie MCP server is live and connected to Cursor!
Next, we interact with the MCP server through Cursor.
Based on the query, it can:
- Fetch detailed information about an existing video.
- Retrieve the video segment where a specific event occurred.
By integrating audio and video context into RAG, devs can build powerful multimedia and multimodal GenAI apps.
​Find the code in this GitHub repo →​
Thanks for reading!
Zero to Hero
The full MCP blueprint
After doing the crash course series on ​RAG​ and ​AI Agents​, we started another one on MCP, which is both foundational and implementation-heavy, walking you through everything step-by-step.
​In Part 1​, we introduce:
- Why context management matters in LLMs.
- The limitations of prompting, chaining, and function calling.
- The M×N problem in tool integrations..
- And how MCP solves it through a structured Host–Client–Server model.
​In Part 2​, we go hands-on and cover:
- The core capabilities in MCP (Tools, Resources, Prompts).
- How JSON-RPC powers communication.
- Transport mechanisms (Stdio, HTTP + SSE).
- A complete, working MCP server with Claude and Cursor.
- Comparison between function calling and MCPs.
​In Part 3​, we built a fully custom MCP client from scratch:
- How to build a custom MCP client and not rely on prebuilt solutions like Cursor or Claude.
- What the full MCP lifecycle looks like in action.
- The true nature of MCP as a client-server architecture, as revealed through practical integration.
- How MCP differs from traditional API and function calling, illustrated through hands-on implementations.
​In Part 4​, we built a full-fledged MCP workflow using tools, resources, and prompts.
- What exactly are resources and prompts in MCP?
- Implementing resources and prompts server-side.
- How tools, resources, and prompts differ from each other.
- Using resources and prompts inside the Claude Desktop.
- A full-fledged real-world use case powered by coordination across tools, prompts, and resources.
​In part 5, we explained the process of integrating Sampling into MCP workflows.
- What is sampling, and why is it useful?
- Sampling support in FastMCP
- How does it work on the server side?
- How to write a sampling handler on the client side?
- Model preferences
- Use cases for sampling
- Error handling and some best practices
This protocol is already powering real-world agentic systems.
And in this crash course, you’ll learn exactly how to implement and extend it, from first principles to production use.
Read the first five parts here:
THAT'S A WRAP
No-Fluff Industry ML resources to
Succeed in DS/ML roles
At the end of the day, all businesses care about impact. That’s it!
- Can you reduce costs?
- Drive revenue?
- Can you scale ML models?
- Predict trends before they happen?
We have discussed several other topics (with implementations) in the past that align with such topics.
Here are some of them:
- Learn sophisticated graph architectures and how to train them on graph data in this crash course.
- So many real-world NLP systems rely on pairwise context scoring. Learn scalable approaches here.
- Run large models on small devices using Quantization techniques.
- Learn how to generate prediction intervals or sets with strong statistical guarantees for increasing trust using Conformal Predictions.
- Learn how to identify causal relationships and answer business questions using causal inference in this crash course.
- Learn how to scale and implement ML model training in this practical guide.
- Learn 5 techniques with implementation to reliably test ML models in production.
- Learn how to build and implement privacy-first ML systems using Federated Learning.
- Learn 6 techniques with implementation to compress ML models.
All these resources will help you cultivate key skills that businesses and companies care about the most.
SPONSOR US
Advertise to 600k+ data professionals
Our newsletter puts your products and services directly in front of an audience that matters — thousands of leaders, senior data scientists, machine learning engineers, data analysts, etc., around the world.
