scripod.com

Inside Stainless: The Developer Tools Startup Anthropic Just Bought for $300 Million

AI & I

May 20
AI & I

AI & I

May 20

Shownote

If your MCP server has dozens of tools, it's probably built wrong. You need tools that are specific and clear for each use case—but you also can't have too many. This creates an almost impossible tradeoff that most companies don't know how to solve. That's why we interviewed Alex Rattray, the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. We get into MCP and the future of the AI-native internet.  [Disclosure: Dan is a small investor in Stainless.] If you found this episode interesting, please like, subscribe, comment, and share. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Get started with Braintrust at https://www.braintrust.dev/  Timestamps:  00:01:15 - Introduction  00:05:09 - APIs and MCP, the connectors of the new internet  00:11:00 - Why MCP exists  00:17:15 - Why MCP servers are hard to get right  00:20:24 - Design principles for reliable MCP servers 00:25:06 - Using MCP for business ops at Stainless  00:40:57 - Alex's take on the security model for MCP  00:44:42 - How one-off AI actions become permanent production software Links to resources mentioned in the episode: Alex Rattray: Alex Rattray (@RattrayAlex), Alex Rattray Stainless: https://www.stainless.com/Inside Stainless: The Developer Tools Startup Anthropic Just Bought for $300 Million

Highlights

This podcast features Alex Rattray, founder of Stainless, discussing the Model Context Protocol (MCP) for connecting AI to the internet. He explores the challenges of designing effective MCP servers, including tool selection, security, and the balance between specificity and scalability. The conversation also covers practical applications of MCP for business operations and the future of AI-native software development.
00:00
MCP connects AI to the internet
01:16
Running barefoot builds toughness
05:11
APIs are the connections enabling computer-to-computer communication
13:58
Exposing all API endpoints exhausts context windows
17:21
Handcrafting tools for LLMs is necessary but difficult.
20:24
Keep the number of tools small and precise.
33:10
AI as cyborgs combining LLMs with traditional code
40:59
Security at the API layer using OAuth with granular scopes
44:50
Taking risks early often leads to faster adoption.

Chapters

MCP connects AI to the internet
00:00
Introduction
01:15
APIs and MCP, the connectors of the new internet
05:09
Why MCP exists
11:00
Why MCP servers are hard to get right
17:15
Design principles for reliable MCP servers
20:24
Using MCP for business ops at Stainless
25:06
Alex's take on the security model for MCP
40:57
How one-off AI actions become permanent production software
44:42

Transcript

Dan Shipper: The internet runs on computers talking to each other, but its entire architecture was built for a pre-AI world. Now we're trying to hook AI up to the internet. With MCP, Model Context Protocol, which turns any website or web service into a set...