Shadowing Practice: MCP Just Got a Whole Lot Better - Learn English Speaking with Video
בחר מצב תרגול
כל מצב פותח חדר תרגול במסך מלא.
61 משפטים
אם המשפטים קצרים או ארוכים מדי, לחץ על ערוך כדי להתאים אותם.
1
MCP is blowing up right now.
2
Agents' usage of MCP is increasing exponentially and it's not showing any signs of slowing down.
3
But at the same time, many agents are now changing the way that they handle tools
4
and starting to take over responsibilities that used to belong to the server.
5
So what does all of this mean for the way that we build MCP servers?
6
Well, let's break it all down.
7
When MCP first hit the scene, one of the most common approaches for building MCP servers was
8
to just map each of your API endpoints to its own tool.
9
And by doing this, an agent was able to access the full range of your API surface area.
10
And this implementation worked, but it presented two major issues.
11
First, if your API had hundreds of endpoints, then that meant your MCP server had hundreds of tools.
12
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.
13
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.
14
In order to solve some of these problems, a lot of MCP servers adopted a layered tool call approach.
15
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,
16
a tool to inspect the definition of a specific endpoint, and a tool to execute the request.
17
This pattern has seen a lot of adoption, but this is now where the big change happens.
18
Traditionally, this pattern was implemented on the MCP server side.
19
But more recently, many MCP clients, especially many popular coding agents, are implementing this pattern on the client side.
20
The pattern is now called progressive tool discovery, and it's a recommended best practice for MCP clients.
21
In addition, a lot of these agents, like Codex or ClaudeCode, are implementing what's called programmatic tool calling, also known as code mode.
22
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.
23
The script then runs in the sandbox, and then only the final result is returned back to the model.
24
Between progressive discovery handling tool call selection and then code mode handling tool composition,
25
the clients are now starting to take more ownership of the problems that servers originally were trying to solve.
26
So surely this means we can just go back to the
27
original method of doing a one-to-one mapping of API endpoints to tool calls, right?
28
Not quite.
29
While an agent certainly can accomplish everything it needs to just by having access to tools that represent every API endpoint,
30
that isn't necessarily always the most efficient way to interact with an API.
31
For any given API, there are often very common tasks or workflows that require stringing together multiple API calls.
32
And if an agent has to figure out that chain on its own every single time, that's a lot of wasted tokens.
33
And this is the same reason that SDKs exist.
34
They give you the raw endpoints but also bundle common workflows into single operations.
35
And we can apply that same idea to the tools that we expose through our MCP server.
36
So for example, with Neon, we have this idea of creating a branch.
37
But it turns out that creating a branch is actually three separate API calls under the hood.
38
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.
39
In the SDK, we bundle those three API calls into one method called createWithCompute.
40
So as this relates to our MCP server, in order to give MCP clients the most token-efficient path possible,
41
it's helpful to expose operations like this that they can take advantage of in some of these common use cases.
42
Of course, if your API is relatively simple and straightforward, a one-to-one mapping might be totally fine.
43
But for something like Neon, where there's some complexity in provisioning infrastructure,
44
these ergonomic shortcuts save the agent from making the same mistakes over and over again.
45
So at Neon, we have an SDK which is generated from from our open API spec.
46
So that way it covers every API endpoint.
47
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.
48
From here, in order for this to be usable by agents, we need to convert all of these methods into tool calls.
49
So that's exactly what we did with a package that we call neon tools.
50
So that includes both the raw endpoints and the ergonomic workflows, all as tool calls.
51
And by virtue of pulling these tools out into a separate package, we're able to serve a few different use cases.
52
First and foremost, in the Neon MCP server, the server imports this package to surface all of these tools to any MCP client.
53
But on top of that, we can also take this package and build adapters around it for different agent frameworks.
54
So for example, we have adapters for both Mastra and Eve for anyone building custom agents with those frameworks.
55
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.
56
All in all, the big idea here is that the server is controlling what tools are available,
57
but then the client handles discovering and executing those tools in whatever way it sees fit.
58
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.
59
ways that you're approaching building your own MCP server?
60
Let us know down in the comments.
61
Thank you so much for watching and I'll see you in the next one.
הורד אפליקציה
כל מה שאתה צריך כדי לדבר בשטף
הגיית AIציון לכל משפט
תרגול IPAשלוט בכל צליל
אוצר מיליםבנה את מאגר המילים שלך
משחק אוצר מיליםלמד תוך כדי משחק
FOR YOU
המלץ על סרטון
C11
143 משפטים
MCP vs API: The protocol every developer needs to know
Business EnglishUniversity StudentsWorking Adults
C11
309 משפטים
Claude Code: The Advanced Guide (99% of Devs Skip These Features)
Business EnglishUniversity StudentsWorking Adults
C112
25 משפטים
Introducing the Agents API
Business EnglishUniversity StudentsWorking Adults
C13
51 משפטים
Business Partner C1. Unit 1. Video 1.1.1.
Business EnglishUniversity StudentsWorking Adults
C1117 משפטים
I've Changed My Opinion On DEVELOPERS Vibe Coding
Business EnglishUniversity StudentsWorking Adults
C16
49 משפטים
What Are Microservices Really All About? (And When Not To Use It)
Business EnglishUniversity StudentsWorking Adults
C14
78 משפטים
Connect Slack to Salesforce with Hosted MCP Servers | Salesforce Headless 360 Decoded
Business EnglishUniversity StudentsWorking Adults
C11
197 משפטים
Unreal Engine 5.8 - Experimental MCP Server Support Walkthrough | State of Unreal 2026
Business EnglishWorking Adults
C12
151 משפטים
Wrote My Own Memory Allocator (and ran DOOM with It)
Business EnglishUniversity StudentsWorking Adults
C12
339 משפטים
Easy Migration from Postgres to Databricks Lakebase
Business EnglishUniversity StudentsWorking Adults
C14
58 משפטים
The mystery is solved... and the answer is 40x cheaper than Claude
American AccentBusiness EnglishUniversity StudentsWorking Adults
C13
200 משפטים
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.
מהי טכניקת השאדואינג?
שאדואינג היא טכניקת למידת שפה מבוססת מדע שפותחה במקור להכשרת מתורגמנים מקצועיים ופופולרית על ידי הפוליגלוט ד"ר אלכסנדר ארגואלס. השיטה פשוטה אך עוצמתית: אתה מקשיב לאודיו באנגלית ילידית וחוזר עליו בקול רם מיד — כמו צל העוקב אחרי הדובר עם עיכוב של 1–2 שניות בלבד. בניגוד להאזנה פסיבית או תרגילי דקדוק, שאדואינג מכריח את המוח והשרירים בפה לעבד ולשחזר דפוסי דיבור אמיתיים בו זמנית. מחקרים מראים שזה משפר משמעותית את דיוק ההגייה, האינטונציה, הקצב, הדיבור המחובר, הבנת השמיעה ושטף הדיבור — מה שהופך אותו לאחת השיטות היעילות ביותר להכנה לIELTS Speaking ולתקשורת באנגלית בעולם האמיתי.