Artwork

Вміст надано Real Python. Весь вміст подкастів, включаючи епізоди, графіку та описи подкастів, завантажується та надається безпосередньо компанією Real Python або його партнером по платформі подкастів. Якщо ви вважаєте, що хтось використовує ваш захищений авторським правом твір без вашого дозволу, ви можете виконати процедуру, описану тут https://uk.player.fm/legal.
Player FM - додаток Podcast
Переходьте в офлайн за допомогою програми Player FM !

Dangers of Automatically Converting a REST API to MCP

1:24:25
 
Поширити
 

Manage episode 507288858 series 2637014
Вміст надано Real Python. Весь вміст подкастів, включаючи епізоди, графіку та описи подкастів, завантажується та надається безпосередньо компанією Real Python або його партнером по платформі подкастів. Якщо ви вважаєте, що хтось використовує ваш захищений авторським правом твір без вашого дозволу, ви можете виконати процедуру, описану тут https://uk.player.fm/legal.

When converting an existing REST API to the Model Context Protocol, what should you consider? What anti-patterns should you avoid to keep an AI agent’s context clean? This week on the show, Kyle Stratis returns to discuss his upcoming book, “AI Agents with MCP”.

Kyle has been busy since he last appeared on the show in 2020. He’s taken his experience working in machine learning startups and started his own consultancy, Stratis Data Labs. He’s been documenting his explorations working with LLMs and MCP on his blog, The Signal Path.

Kyle is also writing a book about building MCP clients, services, and end-to-end agents. We discuss a recent article he wrote about the hazards of using an automated tool to convert a REST API into an MCP server. He shares his personal experiences with building MCP tools and provides additional resources for you to learn more about the topic.

This episode is sponsored by InfluxData.

Spotlight: Python for Beginners: Code With Confidence – Real Python

Learn Programming Fundamentals and Pythonic Coding in Eight Weeks—With a Structured Course

Topics:

  • 00:00:00 – Introduction
  • 00:02:41 – Updates on career
  • 00:04:36 – The Signal Path - newsletter
  • 00:07:15 – Moving into consulting
  • 00:12:35 – Recent projects
  • 00:14:51 – Need for data skills with MCP
  • 00:16:49 – Describing the differences between REST APIs and MCP
  • 00:19:59 – Interaction model differences
  • 00:27:29 – Sponsor: InfluxData
  • 00:28:21 – Agent stories
  • 00:32:58 – Going through a simple example of MCP server
  • 00:37:50 – Defining client and server
  • 00:40:19 – Examples of servers currently
  • 00:51:44 – Announcement: Python for Beginners: Code with Confidence
  • 01:02:07 – Resources for further study
  • 01:05:07 – Breaking down advice on moving an API to MCP
  • 01:08:04 – What are you excited about in the world of Python?
  • 01:18:20 – What do you want to learn next?
  • 01:21:35 – How can people follow your work online?
  • 01:22:46 – Thanks and goodbye

Show Links:

Level up your Python skills with our expert-led courses:

Support the podcast & join our community of Pythonistas

  continue reading

268 епізодів

Artwork
iconПоширити
 
Manage episode 507288858 series 2637014
Вміст надано Real Python. Весь вміст подкастів, включаючи епізоди, графіку та описи подкастів, завантажується та надається безпосередньо компанією Real Python або його партнером по платформі подкастів. Якщо ви вважаєте, що хтось використовує ваш захищений авторським правом твір без вашого дозволу, ви можете виконати процедуру, описану тут https://uk.player.fm/legal.

When converting an existing REST API to the Model Context Protocol, what should you consider? What anti-patterns should you avoid to keep an AI agent’s context clean? This week on the show, Kyle Stratis returns to discuss his upcoming book, “AI Agents with MCP”.

Kyle has been busy since he last appeared on the show in 2020. He’s taken his experience working in machine learning startups and started his own consultancy, Stratis Data Labs. He’s been documenting his explorations working with LLMs and MCP on his blog, The Signal Path.

Kyle is also writing a book about building MCP clients, services, and end-to-end agents. We discuss a recent article he wrote about the hazards of using an automated tool to convert a REST API into an MCP server. He shares his personal experiences with building MCP tools and provides additional resources for you to learn more about the topic.

This episode is sponsored by InfluxData.

Spotlight: Python for Beginners: Code With Confidence – Real Python

Learn Programming Fundamentals and Pythonic Coding in Eight Weeks—With a Structured Course

Topics:

  • 00:00:00 – Introduction
  • 00:02:41 – Updates on career
  • 00:04:36 – The Signal Path - newsletter
  • 00:07:15 – Moving into consulting
  • 00:12:35 – Recent projects
  • 00:14:51 – Need for data skills with MCP
  • 00:16:49 – Describing the differences between REST APIs and MCP
  • 00:19:59 – Interaction model differences
  • 00:27:29 – Sponsor: InfluxData
  • 00:28:21 – Agent stories
  • 00:32:58 – Going through a simple example of MCP server
  • 00:37:50 – Defining client and server
  • 00:40:19 – Examples of servers currently
  • 00:51:44 – Announcement: Python for Beginners: Code with Confidence
  • 01:02:07 – Resources for further study
  • 01:05:07 – Breaking down advice on moving an API to MCP
  • 01:08:04 – What are you excited about in the world of Python?
  • 01:18:20 – What do you want to learn next?
  • 01:21:35 – How can people follow your work online?
  • 01:22:46 – Thanks and goodbye

Show Links:

Level up your Python skills with our expert-led courses:

Support the podcast & join our community of Pythonistas

  continue reading

268 епізодів

Усі епізоди

×
 
Loading …

Ласкаво просимо до Player FM!

Player FM сканує Інтернет для отримання високоякісних подкастів, щоб ви могли насолоджуватися ними зараз. Це найкращий додаток для подкастів, який працює на Android, iPhone і веб-сторінці. Реєстрація для синхронізації підписок між пристроями.

 

Короткий довідник

Слухайте це шоу, досліджуючи
Відтворити