Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

MCP is mind-blowing. Here is a genius setup that will earn you a promotion with your manager. I have multiple data sources: data in S3, MySQL, and local files. Using Spice (an open-source project), I can co-locate all of that data behind a single SQL endpoint and augment it...

142,696 görüntüleme • 1 yıl önce •via X (Twitter)

30 Yorum

Santiago profil fotoğrafı
Santiago1 yıl önce

This will give you 1,000 ideas. The Spice OSS repository is here: If you want to watch the video on YouTube, here is the link:

Assist profil fotoğrafı
Assist2 yıl önce

You can save yourself hundreds of hours every month hiring a personal assistant. At Assist, we can manage any task or project. We help save you time to focus on what matters most to you. Whether you need help growing your business, managing your busy schedule, or doing other personal and business related tasks, we’re here to help. Popular Services Include: 📈 Social Media Management 💸 Ad Campaign Management 💻 Website Management 🎨 Graphic Design 📝 Writing Services 🕒 Schedule Management 🎞️ Photo and Video Editing 🌐 Social Networking 📊 Research & Reports 👍 Task Assistance And More! We'll manage any task within your budget. ✅ Follow us and send us a message to learn more! Follow us on X ➡️ Send us a message ➡️ Visit our website ➡️

Greg Parra profil fotoğrafı
Greg Parra1 yıl önce

Mind-blowing is an understatement. for everything you need

Pol Avec profil fotoğrafı
Pol Avec1 yıl önce

That looks pretty cool. How do you handle the auth to the data sources? Also curious - with your reach in the MCP space, any thoughts on pushing for richer UIs in MCP clients? The text-only experience feels limiting compared to what's possible with even basic HTML/images.

Markus Odenthal profil fotoğrafı
Markus Odenthal1 yıl önce

Awesome finding! My use case would be querying Slack and Confluence. Last week: I run into Kubernetes deployment issues. I solved it by checking Slack history, Confluence pages and ask colleages. Really painful process. This tool could help 🧐

Adam Dorf profil fotoğrafı
Adam Dorf1 yıl önce

I believe MCP like solutions will change everything in time

Meer Shah profil fotoğrafı
Meer Shah1 yıl önce

Brilliant example! I've been sleeping on MCPs thus far but time to wake up This abstracts away the programming layer, you don't see the SQL How do you trust the data to be accurate?

Caique profil fotoğrafı
Caique1 yıl önce

Actually it has nothing related to MCP, you could easily do it with a python script. MCP is just a communication protocol. What happens on software it exposes that matters. This is the reason the protocol is not useful at all. There are tools that already translate your OpenAPI to this new unuseful protocol.

Yaryna Gotlib profil fotoğrafı
Yaryna Gotlib1 yıl önce

This is amazing!!! Thanks a lot for sharing

Hannes Lehmann profil fotoğrafı
Hannes Lehmann1 yıl önce

Someone needs to build an MCP Server for Will it be me?

Michaël Rasoahaingo profil fotoğrafı
Michaël Rasoahaingo1 yıl önce

How do you update data on the tables? or it's live in runtime?

AI Genesis profil fotoğrafı
AI Genesis1 yıl önce

One SQL endpoint for everything? MCP + Spice just became my new favorite duo.

Fizzy profil fotoğrafı
Fizzy1 yıl önce

This is inane. MCPs are the next banger for AI. The usecase s for LLMs just got astronomical.

mike not impossible profil fotoğrafı
mike not impossible1 yıl önce

Very cool, thanks for sharing! It wasn't obvious to me why having the Spice MCP use the tool vs. having the the client use the tool is better?

Jazzy Script profil fotoğrafı
Jazzy Script1 yıl önce

Seems efficient; helps streamline data access.

ryan yang profil fotoğrafı
ryan yang1 yıl önce

Co-locating data via Spice? Smart. Next: audit workflows, track latency. Modular wins—APIs > patchwork. ROI climbs when data flows, not fights. Seen this pattern scale.

Daniel Meacham profil fotoğrafı
Daniel Meacham1 yıl önce

I see the integration to cursor. How would this work if you would expose it in the app itself?

Karl Mehta profil fotoğrafı
Karl Mehta1 yıl önce

Absolutely genius.

V profil fotoğrafı
V1 yıl önce

🫨

alex profil fotoğrafı
alex1 yıl önce

it is easier interacting with a sql database to just write plain sql than to use an mcp

Pawan Gangwani profil fotoğrafı
Pawan Gangwani1 yıl önce

Is it standard way to create wrapper on top of multiple mcp servers ?

Shane Kempton profil fotoğrafı
Shane Kempton1 yıl önce

It sure is. We’re seeing unreal new use cases every week.

AJ Chadha profil fotoğrafı
AJ Chadha1 yıl önce

👀

erdinaryus profil fotoğrafı
erdinaryus1 yıl önce

Thank you ! Nice content.

Dirk Roeckmann profil fotoğrafı
Dirk Roeckmann1 yıl önce

And now do it in a critical business scenario at scale and in production in a non-verifiable domain. What’s the rate of syntactically invalid SQL queries and what’s the rate of syntactically valid but semantically wrong SQL queries? What’s the rate of verifiable reproducibility for a specific resultset given a series of identical queries? I am curios … #AI #MCP

CodingTheSmartWay profil fotoğrafı
CodingTheSmartWay1 yıl önce

This looks cool ... thanks for sharing!

ⲯ 𝓑𝓲𝓹𝓲 ⲯ profil fotoğrafı
ⲯ 𝓑𝓲𝓹𝓲 ⲯ1 yıl önce

Unfortunately from someone who built and hacked DBs for a long time, this is not the groundbreaking as it looks, you can do most of these things with a simple SQL query...

Radoslav Stefanov profil fotoğrafı
Radoslav Stefanov1 yıl önce

You can achieve the same results with some bash magic and clever local caching. If not better/faster. With less dependencies. So where is the mind blowing part? 🤔

Shiv J. profil fotoğrafı
Shiv J.1 yıl önce

Do you think MCP is only useful in a dev environment? Most MCP examples I’ve seen are through Cursor or IDEs. have also read a lot of your posts but trying to get an intuitive sense of why MCP is better than function calling. Are there resources you read that made it click?

Saïd Aitmbarek profil fotoğrafı
Saïd Aitmbarek1 yıl önce

so bullish on MCP, A2A and more protocols to come for the agentic era

Benzer Videolar

Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.

Akshay 🚀

39,331 görüntüleme • 5 ay önce

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,010 görüntüleme • 1 yıl önce

MCP is an absolute game-changer. (Together with DeepSeek, MCP is probably the hottest thing in AI over the last 6 months.) I use Cursor to write code 90% of the time. I built an MCP server to connect the Cursor agent to GroundX, an open-source RAG system, and I'm not going back. This is officially insane! Here is what I did, step by step: First, a little bit of context. I maintain an end-to-end Machine Learning System with several pipelines to process data, train, evaluate, register, deploy, and monitor a model. I've written a lot of documentation explaining how the system works and how to modify and maintain it. There's also the documentation of the few libraries I used to build the system. I'm a massive fan of GroundX, an open-source enterprise-grade RAG system you can run on your servers or deploy to any cloud provider. I've been working with them for a long time. GroundX offers two services. First, the "ingest" service uses a custom, pretrained vision model to ingest and understand your data. I used this to process all the documentation I have for my code. Markdown files, source code, HTML files, and even PDF documents. Everything I've written related to my project went into GroundX. Their second service is "search," which combines text and vector search with a fine-tuned re-ranker model to retrieve information from the data. I needed to connect Cursor with this service, and that's where MCP came in. I built an MCP server with two tools: 1. The first tool would go to GroundX and retrieve the available topics. Splitting the data into topics (or "buckets," as GroundX calls them) allows me to use the same setup to serve documentation from different topics. 2. The second tool would search GroundX under a specific topic for the context related to the supplied query. The magic happens after connecting the MCP server with Cursor. Now, I can ask any questions related to my project, and Cursor's AI agent retrieves the list of available topics from the RAG system and then searches it to provide relevant context to the model. I went from getting mediocre, sometimes wrong answers to 100% truthful, complete answers. Here is the crazy part:

Santiago

255,532 görüntüleme • 1 yıl önce