High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works
← All source episodes

Latent Space / episode intelligence

The Creators of Model Context Protocol

3 Apr 2025 26 published claims 2 attributable people
Open original episode ↗ Read the evidence

Speakers in the public record

Shawn WangAlessio Fanelli

Claim mix

belief 10evaluation 8recommendation 4preference 2commitment 1observation 1

Evidence policy

Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.

Claim ledger

The useful parts, with receipts.

26 published records

01 / evaluation

There's a deliberate design decision to make the protocol somewhat stateful because we do really believe that AI applications and AI like interactions will become inherently more stateful and that we're the current state of like, like need for statelessness is more a temporary point in time that will, you know, to some degree that will always exist.

“There's a deliberate design decision to make the protocol somewhat stateful because we do really believe that AI applications and AI like interactions will become inherently more stateful and that we're the current state of like, like need for statelessness is more a temporary point in time that will, you know, to some degree that will always exist.”
Speaker
Not verified from transcript
Publisher
Latent Space

04 / evaluation

I think almost immediately after that conversation and then, I don't know, it was a couple, maybe a few months of, uh, building the really unrewarding bits, if we're being honest, because for, for establishing something that's like this communication protocol has clients and servers and like SDKs everywhere, there's just like a lot of like laying the groundwork that you have to do.

“I think almost immediately after that conversation and then, I don't know, it was a couple, maybe a few months of, uh, building the really unrewarding bits, if we're being honest, because for, for establishing something that's like this communication protocol has clients and servers and like SDKs everywhere, there's just like a lot of like laying the groundwork that you have to do.”
Speaker
Not verified from transcript
Publisher
Latent Space

05 / evaluation

I think fundamentally we every sort of primitive that we thought through, we thought from the perspective of the application developer first, like if I'm building an application, whether it is an IDE or, you know, call a desktop or some agent interface or whatever the case may be, what are the different things that I would want to receive from like an integration?

“I think fundamentally we every sort of primitive that we thought through, we thought from the perspective of the application developer first, like if I'm building an application, whether it is an IDE or, you know, call a desktop or some agent interface or whatever the case may be, what are the different things that I would want to receive from like an integration?”
Speaker
Not verified from transcript
Publisher
Latent Space

06 / evaluation

I think agentically that you requires an LLM call and like a one form of fashion, like for summarization or so, but I'm staying model independent and for that, that's where like part of this by directionality comes in, in this more rich experience where we do have this facility for servers to ask the client again, who owns the LLM interaction, right?

“I think agentically that you requires an LLM call and like a one form of fashion, like for summarization or so, but I'm staying model independent and for that, that's where like part of this by directionality comes in, in this more rich experience where we do have this facility for servers to ask the client again, who owns the LLM interaction, right?”
Speaker
Not verified from transcript
Publisher
Latent Space

07 / preference

And I was mostly working on internal developer tooling, which is what I've been doing for like years and years before. And as part of that, I think there was an effort of like, how do I empower more like employees at Anthropic to use, you know, to integrate really deeply with the models we have?

“And I was mostly working on internal developer tooling, which is what I've been doing for like years and years before. And as part of that, I think there was an effort of like, how do I empower more like employees at Anthropic to use, you know, to integrate really deeply with the models we have?”
Speaker
Not verified from transcript
Publisher
Latent Space

12 / belief

I think both, like, I, I think there, there will always be value in like, oh, I have, you know, I have my data over here, and I want to use some connector to bring it into my application over here.

“I think both, like, I, I think there, there will always be value in like, oh, I have, you know, I have my data over here, and I want to use some connector to bring it into my application over here.”
Speaker
Not verified from transcript
Publisher
Latent Space

14 / belief

I think honestly, this is one of the most contentious topics we've discussed as like the core MCP team and like gone through multiple iterations on and back and forth.

“I think honestly, this is one of the most contentious topics we've discussed as like the core MCP team and like gone through multiple iterations on and back and forth.”
Speaker
Not verified from transcript
Publisher
Latent Space

15 / belief

We really want the client applications to have full control in the MCP paradigm. That in addition, though, like I think there, one thing that's very, very early in my thinking is there might be a addition to the protocol where you want to give the server author the ability to like logically group certain primitives together, potentially.

“We really want the client applications to have full control in the MCP paradigm. That in addition, though, like I think there, one thing that's very, very early in my thinking is there might be a addition to the protocol where you want to give the server author the ability to like logically group certain primitives together, potentially.”
Speaker
Not verified from transcript
Publisher
Latent Space

18 / belief

I mean, I think we've clearly done a lot of work. But I think we really need to be able to shift and like, you know, extract the information it cares about, because that's what that's exactly what they excel at.

“I mean, I think we've clearly done a lot of work. But I think we really need to be able to shift and like, you know, extract the information it cares about, because that's what that's exactly what they excel at.”
Speaker
Not verified from transcript
Publisher
Latent Space

19 / recommendation

So abusing the trust system is like setting up a trust system creates the damage from the trust system. And so I actually want to encourage people to try out MCP Inspector because all you got to do is actually just look at the traffic.

“So abusing the trust system is like setting up a trust system creates the damage from the trust system. And so I actually want to encourage people to try out MCP Inspector because all you got to do is actually just look at the traffic.”
Speaker
Shawn Wang
Publisher
Latent Space

23 / evaluation

Totally. And I think that is partially why it made your launch successful because you launch with a sufficiently spanning set of here's examples and then people just copy paste and expand from there.

“Totally. And I think that is partially why it made your launch successful because you launch with a sufficiently spanning set of here's examples and then people just copy paste and expand from there.”
Speaker
Shawn Wang
Publisher
Latent Space

25 / recommendation

Like they're, they're not normal servers in the, in the sense that they, they wrap some API and it's just easier to interact with those than to work at the APIs. And so I'll, I'll highlight the, the memory one first, just because like, I think there are, there are a few memory startups, but actually you don't need them if you just use this one.

“Like they're, they're not normal servers in the, in the sense that they, they wrap some API and it's just easier to interact with those than to work at the APIs. And so I'll, I'll highlight the, the memory one first, just because like, I think there are, there are a few memory startups, but actually you don't need them if you just use this one.”
Speaker
Shawn Wang
Publisher
Latent Space

26 / evaluation

You know, I think you, you maybe have a published some research that says like, actually sometimes to get, to get the model working the right way, you have to do multi-step prompting or jailbreaking to, to, to behave the way that you want.

“You know, I think you, you maybe have a published some research that says like, actually sometimes to get, to get the model working the right way, you have to do multi-step prompting or jailbreaking to, to, to behave the way that you want.”
Speaker
Shawn Wang
Publisher
Latent Space
Search evidence