Loading video...

Video Failed to Load

Go Home

Wanted to learn more about MCPs this weekend. So I built this mini-tool called Here is how it works: 1️⃣ Tell the AI what you want. 2️⃣ It creates an MCP server with various tools. 3️⃣ Talk with AI to add/remove/modify these tools. 4️⃣ Click on Deploy and get...

108,366 views • 1 year ago •via X (Twitter)

11 Comments

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

Added instructions on how to add the generated MCP server to Claude Desktop / Cursor / Windsurf

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

I have already run out of @AnthropicAI credits 😅 Just recharged again.

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

😅

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

More than 100 MCP Servers got created in < 2 hrs 🤯

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

Hitting concurrency rate limits for Claude API. Can someone from @AnthropicAI please help?

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

Going to add fallbacks to @OpenAI No other way around.

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

I had max_tokens set to 4192, but many MCP servers are much more than 4192. So it was erroring out. Increased it to a much higher value now.

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

If you want to create an mcp server for an existing api, you can do it like this. Just give it an example curl request, and it will create an mcp server based on that.

PDF GPT's profile picture
PDF GPT1 year ago

This is my favorite AI tool for reviewing reports. Just upload a report, ask for a summary, and get one in seconds. It's like ChatGPT, but built for documents. Try it for free.

Adithya launching Indie.Deals V2 🚀's profile picture
Adithya launching Indie.Deals V2 🚀1 year ago

As a teetotaller, for a moment I thought I was drunk while trying it out because of the floating input card. 😅 Such a simple execution. Is there a way to also see what people have already created so I can use something existing instead of a creating a new one?

Bhanu Teja P's profile picture
Bhanu Teja P1 year ago

That’s a good idea. Will show what others have created.

Related Videos

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

141,952 views • 1 year ago