ฝึกพูดภาษาอังกฤษด้วยเทคนิค Shadowing จากวิดีโอ: MCP Just Got a Whole Lot Better

เลือกโหมดฝึก

แต่ละโหมดจะเปิดห้องฝึกแบบเต็มจอ

61 ประโยค

หากประโยคสั้นหรือยาวเกินไป กดที่ Edit เพื่อปรับแก้

MCP is blowing up right now.

Agents' usage of MCP is increasing exponentially and it's not showing any signs of slowing down.

But at the same time, many agents are now changing the way that they handle tools

and starting to take over responsibilities that used to belong to the server.

So what does all of this mean for the way that we build MCP servers?

Well, let's break it all down.

When MCP first hit the scene, one of the most common approaches for building MCP servers was

to just map each of your API endpoints to its own tool.

And by doing this, an agent was able to access the full range of your API surface area.

And this implementation worked, but it presented two major issues.

First, if your API had hundreds of endpoints, then that meant your MCP server had hundreds of tools.

And all of these tools would be loaded into the context window up front, meaning that before you even started your session, your context window could have been completely bloated by MCP tools.

And secondly, if you had lots of endpoints that were similar to each other, an agent might end up getting confused and not pick the right tool for the job.

In order to solve some of these problems, a lot of MCP servers adopted a layered tool call approach.

So now, instead of listing out hundreds of tool calls, you might just have two or three, You might have a tool to search all of the available endpoints,

a tool to inspect the definition of a specific endpoint, and a tool to execute the request.

This pattern has seen a lot of adoption, but this is now where the big change happens.

Traditionally, this pattern was implemented on the MCP server side.

But more recently, many MCP clients, especially many popular coding agents, are implementing this pattern on the client side.

The pattern is now called progressive tool discovery, and it's a recommended best practice for MCP clients.

In addition, a lot of these agents, like Codex or ClaudeCode, are implementing what's called programmatic tool calling, also known as code mode.

With code mode, instead of calling tools one at a time, the agent will go ahead and write a script that chains those tools together in a sandbox environment.

The script then runs in the sandbox, and then only the final result is returned back to the model.

Between progressive discovery handling tool call selection and then code mode handling tool composition,

the clients are now starting to take more ownership of the problems that servers originally were trying to solve.

So surely this means we can just go back to the

original method of doing a one-to-one mapping of API endpoints to tool calls, right?

Not quite.

While an agent certainly can accomplish everything it needs to just by having access to tools that represent every API endpoint,

that isn't necessarily always the most efficient way to interact with an API.

For any given API, there are often very common tasks or workflows that require stringing together multiple API calls.

And if an agent has to figure out that chain on its own every single time, that's a lot of wasted tokens.

And this is the same reason that SDKs exist.

They give you the raw endpoints but also bundle common workflows into single operations.

And we can apply that same idea to the tools that we expose through our MCP server.

So for example, with Neon, we have this idea of creating a branch.

But it turns out that creating a branch is actually three separate API calls under the hood.

You have to first create the branch itself, but then make a separate call to attach compute resources to the branch, and make a third call to get the connection string.

In the SDK, we bundle those three API calls into one method called createWithCompute.

So as this relates to our MCP server, in order to give MCP clients the most token-efficient path possible,

it's helpful to expose operations like this that they can take advantage of in some of these common use cases.

Of course, if your API is relatively simple and straightforward, a one-to-one mapping might be totally fine.

But for something like Neon, where there's some complexity in provisioning infrastructure,

these ergonomic shortcuts save the agent from making the same mistakes over and over again.

So at Neon, we have an SDK which is generated from from our open API spec.

So that way it covers every API endpoint.

But on top of that generated layer, we also have another thinner layer that adds the ergonomic methods that we were just talking about, things like create with compute.

From here, in order for this to be usable by agents, we need to convert all of these methods into tool calls.

So that's exactly what we did with a package that we call neon tools.

So that includes both the raw endpoints and the ergonomic workflows, all as tool calls.

And by virtue of pulling these tools out into a separate package, we're able to serve a few different use cases.

First and foremost, in the Neon MCP server, the server imports this package to surface all of these tools to any MCP client.

But on top of that, we can also take this package and build adapters around it for different agent frameworks.

So for example, we have adapters for both Mastra and Eve for anyone building custom agents with those frameworks.

And one more thing worth noting is that these tools are organized into categories, so that way you can scope down exactly which tools you want the agent to have access to.

All in all, the big idea here is that the server is controlling what tools are available,

but then the client handles discovering and executing those tools in whatever way it sees fit.

All of this is open source, so if you want to dive through the code and see exactly how everything is implemented, I'll have some links down in the description for you to check out.

ways that you're approaching building your own MCP server?

Let us know down in the comments.

Thank you so much for watching and I'll see you in the next one.

ดาวน์โหลดแอป

ทุกอย่างที่ต้องใช้เพื่อพูดได้คล่อง

AI ให้คะแนนการออกเสียงให้คะแนนทุกประโยค

ฝึก IPAเชี่ยวชาญทุกเสียง

คำศัพท์สร้างคลังคำของคุณ

เกมคำศัพท์เล่นไปเรียนไป

สแกน QR

Download on theApp Store Get it onGoogle Play

FOR YOU

วิดีโอแนะนำ

143 ประโยค

Connect Slack to Salesforce with Hosted MCP Servers | Salesforce Headless 360 Decoded

Business EnglishUniversity StudentsWorking Adults

197 ประโยค

Unreal Engine 5.8 - Experimental MCP Server Support Walkthrough | State of Unreal 2026

Business EnglishWorking Adults

151 ประโยค

Wrote My Own Memory Allocator (and ran DOOM with It)

Business EnglishUniversity StudentsWorking Adults

339 ประโยค

Easy Migration from Postgres to Databricks Lakebase

Business EnglishUniversity StudentsWorking Adults

58 ประโยค

The mystery is solved... and the answer is 40x cheaper than Claude

Business EnglishUniversity StudentsWorking Adults

200 ประโยค

CAP Theorem in System Design Interviews

Business EnglishInterview EnglishUniversity Students

Vocabulary and speaking notes for this lesson

This C1 speaking lesson is built on the video “MCP Just Got a Whole Lot Better”. The speaker keeps coming back to these words: tool, Mcp, agent, Api, server. This video has 61 sentences and 1064 words to shadow. The speech runs for 5:55. The speaker talks fast, about 180 words per minute, so expect linked and reduced sounds. Only 81% of the words are among the 3,000 most common in English, so the vocabulary is demanding.

Key vocabulary in this video

The 15 most advanced words in the video, with pronunciation and meaning:

Word	Pronunciation	Meaning
endpoint noun		Either of the two points at the ends of a line segment.
neon noun	/ˈniˌɑn/	The chemical element (symbol Ne) with an atomic number of 10. The second of the noble gases, it is a colourless, odorless inert gas.
ergonomic adjective		Of or relating to the science of ergonomics.
workflow noun	/ˈwɝkfloʊ/	The flowrate at which a flow of work takes place.
compute verb	/kəmˈpjuːt/	To reckon, calculate.
sandbox noun	/ˈsæn(d).bɑks/	A children's play area consisting of a box filled with sand.
adapter noun	/əˈdæptəɹ/	One who is capable of adapting to differing situations.
token noun	/ˈtoʊkən/	Something serving as an expression of something else.
bundle noun	/ˈbʌn.dl̩/	A group of objects held together by wrapping or tying.
execute verb	/ˈɛksɪˌkjuːt/	To kill, especially as punishment for a capital crime.
expose verb	/ɪkˈspoʊz/	To reveal; to uncover; to make visible; to bring to light.
exponentially adverb	/ɛkspə(ʊ)ˈnɛnʃəli/	In an exponential manner.
programmatic adjective	/ˌpɹəʊ.ɡɹəˈmæt.ɪk/	Of, relating to, or using a step-by-step program—especially a computer program.
shortcut noun	/ˈʃɔːtkʌt/	A path between two points that is faster than the commonly used paths.
usable adjective	/ˈjuː.zə.bəl/	Capable of being used.

Phrasal verbs you will hear

Word	Pronunciation	Meaning
blow up verb		To explode or be destroyed by explosion.
check out verb		To record the departure or withdrawal of someone or something (such as guests, employees, books, etc.).
end up verb		To bring to a conclusion.
figure out verb		To come to understand; to discover or find a solution; to deduce.
go ahead verb	/ˌɡoʊ əˈhɛd/	To proceed with; to begin.
go back to verb		To stem from; to originate in.
slow down verb		To decelerate.
take over verb		To assume control of something, such as a business or enterprise, and sometimes by force.

Pronunciation to watch

The speaker uses 5 contractions and reduced forms, such as I'll, isn't, we're. Say them the short way, as you hear them.

The “sh” and “zh” sounds: exponentially /ɛkspə(ʊ)ˈnɛnʃəli/, shortcut /ˈʃɔːtkʌt/, speculation /ˌspɛk.jəˈleɪ.ʃən/, accomplish /əˈkɑm.plɪʃ/, traditionally /tɹəˈdɪʃ.ə.nə.li/
Long words — get the stress right: exponentially /ɛkspə(ʊ)ˈnɛnʃəli/, programmatic /ˌpɹəʊ.ɡɹəˈmæt.ɪk/, speculation /ˌspɛk.jəˈleɪ.ʃən/, complexity /kəmˈplɛk.sɪ.ti/, traditionally /tɹəˈdɪʃ.ə.nə.li/

How to practise with this video

Listen to the whole video once without speaking and note the words you do not know.
Start at 0.75× speed, shadow it sentence by sentence, then go back to normal speed once it feels easy.
Record yourself and compare with the original, paying attention to words like endpoint, neon, ergonomic.

เทคนิค Shadowing คืออะไร?

Shadowing เป็นเทคนิคการเรียนรู้ภาษาที่ได้รับการรับรองทางวิทยาศาสตร์ พัฒนาขึ้นสำหรับการฝึกนักแปลมืออาชีพ วิธีการนี้เรียบง่ายแต่ทรงพลัง: คุณฟังเสียงภาษาอังกฤษจากเจ้าของภาษาและพูดตามทันที — เหมือนเงาที่ตามผู้พูดด้วยช่วงเวลาห่าง 1-2 วินาที การวิจัยแสดงว่าเทคนิคนี้ปรับปรุงความแม่นยำในการออกเสียง ทำนองเสียง จังหวะ การเชื่อมเสียง การฟังเข้าใจ และความคล่องแคล่วในการพูดได้อย่างมีนัยสำคัญ

เทคนิค shadowing: อ่านคู่มือฉบับเต็มทีละขั้นตอน →

ฝึกพูดภาษาอังกฤษด้วยเทคนิค Shadowing จากวิดีโอ: MCP Just Got a Whole Lot Better

เลือกโหมดฝึก

ดาวน์โหลดแอป

MCP vs API: The protocol every developer needs to know

Claude Code: The Advanced Guide (99% of Devs Skip These Features)

Introducing the Agents API

Business Partner C1. Unit 1. Video 1.1.1.

I've Changed My Opinion On DEVELOPERS Vibe Coding

What Are Microservices Really All About? (And When Not To Use It)

Connect Slack to Salesforce with Hosted MCP Servers | Salesforce Headless 360 Decoded

Unreal Engine 5.8 - Experimental MCP Server Support Walkthrough | State of Unreal 2026

Wrote My Own Memory Allocator (and ran DOOM with It)

Easy Migration from Postgres to Databricks Lakebase

The mystery is solved... and the answer is 40x cheaper than Claude

CAP Theorem in System Design Interviews

Vocabulary and speaking notes for this lesson

Key vocabulary in this video

Phrasal verbs you will hear

Pronunciation to watch

How to practise with this video

เทคนิค Shadowing คืออะไร?