Loading video...

Video Failed to Load

Go Home

Here's how to build an MCP server with a single TypeScript file, and connect it to Claude Code. No build step. No bullshit. Totally transformative.

mattpocockuk's profile picture

Matt Pocock

287,453 subscribers

254,095 views • 1 year ago •via X (Twitter)

GamingEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

11 Comments

Matt Pocock's profile picture
Matt Pocock1 year ago

Here's the code, and a link for sharing outside of X.

Christian Esmann's profile picture
Christian Esmann1 year ago

I just launched an all-in-one template for cross-platform development, based on the stack I use myself everyday. Expo, NextJS, TypeScript, Tailwind, Firebase, AppsFlyer, Authentication, Analytics, In-App Purchases, Stripe and a lot more, setup by default.

Tom Hopkins's profile picture
Tom Hopkins1 year ago

after reading their docs and some thought, it's just tool calling? the analog that works best for me is that MCP is like an LSP.

Matt Pocock's profile picture
Matt Pocock1 year ago

I like Anthropic's analogy that MCP is like a USB - just a way of connecting things together

Justin Reidy's profile picture
Justin Reidy1 year ago

@jhooks This is great, thanks for sharing

Jean-Paul's profile picture
Jean-Paul1 year ago

I see you sped up, and didn't wait a week nice

Jean Manzo's profile picture
Jean Manzo1 year ago

You made me go and research the whole concept of MCPs 😂 Thanks TODO: Add it to the membership in TotalTypescript 👍

Virgile RIETSCH's profile picture
Virgile RIETSCH1 year ago

Thank you for the video Matt ! Always straight to the point, I love it!

Emeric HUNTER's profile picture
Emeric HUNTER1 year ago

@vlucas building code is like cooking; simplify the recipe for better results.

cam 🏴‍☠️'s profile picture
cam 🏴‍☠️1 year ago

This is away @mattpocockuk ! Thank you ☺️

Divyansh Gandhi's profile picture
Divyansh Gandhi1 year ago

Wow. Real good video. Thank you!

Related Videos

You can build a MCP business With just 5 lines of code, you can: 1. Setup your own MCP server to connect anything 2. Distribute to thousands of people... No bullshit. 👇
11:32

You can build a MCP business With just 5 lines of code, you can: 1. Setup your own MCP server to connect anything 2. Distribute to thousands of people... No bullshit. 👇

Jason Zhou

77,283 views • 1 year ago

Build a 100% local, private, and secure MCP client. You can connect it to any MCP server. Step-by-step guide:
14:53

Build a 100% local, private, and secure MCP client. You can connect it to any MCP server. Step-by-step guide:

Akshay 🚀

15,560 views • 6 months ago

MCP meets Ollama! In this video you'll learn how build a 100% local MCP client that you can connect to any MCP server. 100% open-source code, step-by-step guide:
14:53

MCP meets Ollama! In this video you'll learn how build a 100% local MCP client that you can connect to any MCP server. 100% open-source code, step-by-step guide:

Akshay 🚀

92,245 views • 1 year ago

Here's how to build an MCP server (for beginners, in 1 minute)
1:09

Here's how to build an MCP server (for beginners, in 1 minute)

dylan

30,846 views • 1 year ago

New Video - Build a real-world MCP server with one TypeScript file. • Zero to live in 10 minutes (live coding from scratch) • Integrates real APIs + API keys • Connects to Anthropic Claude Code via stdio • Orchestrates multiple API calls into 1 action + more
11:14

New Video - Build a real-world MCP server with one TypeScript file. • Zero to live in 10 minutes (live coding from scratch) • Integrates real APIs + API keys • Connects to Anthropic Claude Code via stdio • Orchestrates multiple API calls into 1 action + more

nader dabit

76,870 views • 1 year ago

Chat with Claude Sonnet 3.7 to build your own MCP server. And publish it to GitHub with just a single click. All of this in less than 2 mins.
0:21

Chat with Claude Sonnet 3.7 to build your own MCP server. And publish it to GitHub with just a single click. All of this in less than 2 mins.

Shubham Saboo

69,126 views • 1 year ago

The easiest way to build an MCP Server using Google DeepMind Gemini 2.5 Pro and get started! 1. Use Gitingest to get all the code and docs from the FastMCP repo 2. Download the code into a txt file 3. Go to AI Studio, upload the file, define what kind of MCP Server you want to build 4. Gemini 2.5 Pro builds it for you.
0:40

The easiest way to build an MCP Server using Google DeepMind Gemini 2.5 Pro and get started! 1. Use Gitingest to get all the code and docs from the FastMCP repo 2. Download the code into a txt file 3. Go to AI Studio, upload the file, define what kind of MCP Server you want to build 4. Gemini 2.5 Pro builds it for you.

Philipp Schmid

75,968 views • 1 year ago

Here is how you can build an MCP server with I built an MCP server that can send emails with Resend in < 1 min. Didn't need to write any code.
1:35

Here is how you can build an MCP server with I built an MCP server that can send emails with Resend in < 1 min. Didn't need to write any code.

Bhanu Teja P

20,595 views • 1 year ago

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:
1:48

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

Andrew Ng

81,563 views • 9 months ago

Build in Lovable, from Claude. New native integrations with our MCP server = chat to Claude, export from Claude Design, and ship with Claude Code, directly to Lovable. To get started, go to Claude → Click on the + sign → Connectors → Browse Connectors → Lovable.
0:39

Build in Lovable, from Claude. New native integrations with our MCP server = chat to Claude, export from Claude Design, and ship with Claude Code, directly to Lovable. To get started, go to Claude → Click on the + sign → Connectors → Browse Connectors → Lovable.

Lovable

68,179 views • 13 days ago

Here's how to build your first MCP tool and server with less than 10 Lines of Python code🐍✨ Tried to make this video as short as possible and show the code, the json config and running the server in vs code with github copilot💜
3:43

Here's how to build your first MCP tool and server with less than 10 Lines of Python code🐍✨ Tried to make this video as short as possible and show the code, the json config and running the server in vs code with github copilot💜

Marlene Mhangami

14,603 views • 11 months ago

In case you missed it, earlier this week we launched "MCP: Build Rich-Context AI Apps with Anthropic." Enroll now and: ✅ Explore how MCP standardizes access to tools and data for AI applications, its underlying architecture, and how it simplifies the integration of new tools and connections to external systems (e.g., GitHub repos, Google Docs, local files). ✅ Build and deploy an MCP server that provides tools, resources, and prompts, and add it to the configuration of AI applications, such as Claude Desktop, to extend them. ✅ Build an MCP-compatible application that hosts multiple MCP clients, each maintaining 1-to-1 connection to an MCP server. Join in for free:
1:09

In case you missed it, earlier this week we launched "MCP: Build Rich-Context AI Apps with Anthropic." Enroll now and: ✅ Explore how MCP standardizes access to tools and data for AI applications, its underlying architecture, and how it simplifies the integration of new tools and connections to external systems (e.g., GitHub repos, Google Docs, local files). ✅ Build and deploy an MCP server that provides tools, resources, and prompts, and add it to the configuration of AI applications, such as Claude Desktop, to extend them. ✅ Build an MCP-compatible application that hosts multiple MCP clients, each maintaining 1-to-1 connection to an MCP server. Join in for free:

DeepLearning.AI

23,829 views • 1 year ago

You can now push what you’re building in Claude Code directly into Figma. With the latest updates to the Figma MCP server, build a working prototype in code, then send it to a Figma canvas to explore multiple versions.
0:30

You can now push what you’re building in Claude Code directly into Figma. With the latest updates to the Figma MCP server, build a working prototype in code, then send it to a Figma canvas to explore multiple versions.

Claude

4,309,999 views • 4 months ago

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!
2:43

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 views • 1 year ago

You can now add Claude Code to any vibe coded app. We just launched the new Claude Code integration on vibecode.dev. Which allows you to build fully Agentic Applications. In a single prompt, with no API Key. Here's is an example and tutorial: 0:00 - Claude Code for Twitter Example 01:52 - Building the Claude Code for Motion Graphics
4:53

You can now add Claude Code to any vibe coded app. We just launched the new Claude Code integration on vibecode.dev. Which allows you to build fully Agentic Applications. In a single prompt, with no API Key. Here's is an example and tutorial: 0:00 - Claude Code for Twitter Example 01:52 - Building the Claude Code for Motion Graphics

Riley Brown

30,119 views • 4 months ago

Here's how to build Polymarket NBA bond automations with Claude Code. End-to-end in under 90 seconds.
1:18

Here's how to build Polymarket NBA bond automations with Claude Code. End-to-end in under 90 seconds.

GrandEx

20,948 views • 4 months ago

Claude Code can now connect to remote MCP servers. Pull context from your tools directly into Claude Code with no local setup required.
0:20

Claude Code can now connect to remote MCP servers. Pull context from your tools directly into Claude Code with no local setup required.

Anthropic

540,378 views • 1 year ago

A Mini Crash-Course on MCP! Yesterday, I published a guide that covers: - What MCP is - How to build your own MCP server - How to create a 100% local MCP client - Using this to control & automate any browser Step-by-step guide...👇
0:25

A Mini Crash-Course on MCP! Yesterday, I published a guide that covers: - What MCP is - How to build your own MCP server - How to create a 100% local MCP client - Using this to control & automate any browser Step-by-step guide...👇

Akshay 🚀

66,623 views • 10 months ago

No client can say no to you if you learn how to do this. I went from discovery call to finished spanish client deck in under 2 minutes. Here's how I did it: Step 1: Open Claude Step 2: Connect Gmail, Notion, and gammaapp via MCP (one click each, no API keys) Step 3: "Pull the key points from my discovery call notes in Gmail" Step 4: "Grab the client overview from Notion" Step 5: "Build a campaign proposal deck in Gamma using both" A full deck appeared Check here to start:
0:58

No client can say no to you if you learn how to do this. I went from discovery call to finished spanish client deck in under 2 minutes. Here's how I did it: Step 1: Open Claude Step 2: Connect Gmail, Notion, and gammaapp via MCP (one click each, no API keys) Step 3: "Pull the key points from my discovery call notes in Gmail" Step 4: "Grab the client overview from Notion" Step 5: "Build a campaign proposal deck in Gamma using both" A full deck appeared Check here to start:

Oluwatimileyin✨🦋

89,017 views • 4 months ago

Developers: MCP is about to become extremely relevant as AI needs to connect with real-world data. The problem? Most don't know how to build MCP plugins yet. Here's how to build them with Cline in 3 simple steps using our .clinerules protocol. Thread 🧵
1:52

Developers: MCP is about to become extremely relevant as AI needs to connect with real-world data. The problem? Most don't know how to build MCP plugins yet. Here's how to build them with Cline in 3 simple steps using our .clinerules protocol. Thread 🧵

Cline

189,177 views • 1 year ago