Model Context Protocol, every mention
29 scenes (2026), the whole family · ← back to Model Context Protocol
tap a year for its mentions
every year 2026 anyone Alessio Fanelli 118Shawn Wang 85Saoud (Saud) Rizwan 37David Soria Parra 31Nick Cooper / Brad 13Rohit Agarwal 10Antonio Scandurra 10Walden Yan 9Soham Ganatra 9Nina Lopatina 8
Verbatim, from the transcripts: the passages where Model Context Protocol comes up
Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten
- ▶ 9:37 Shawn Wang And MCP is just another form of tool, right?
OpenAI’s Vision for the AI Super App — Akshay Nathan, OpenAI
- ▶ 50:45 Shawn Wang I do think that just relying on, like, just-in-time pulling of data for, let's say, via MCP, CLI, API, whatever you, whatever you do, still not enough. 2 times in the scene
The AI Frontier: from open weights to open research — Eiso Kant, Poolside AI
GitHub’s Agent Era: 14x Commits, 200M Developers, Copilot’s Next Act — Kyle Daigle
- ▶ 12:54 Kyle Daigle You know, it's usually like, uh, how do like a single skill that's going to identify the most important marketing information, given any MCP server, like this is the most important thing less about.
Devin’s 80% Moment: Background Agents, 7x PRs, & End of Hand-Held Coding — Walden Yan & Cole Murray
- ▶ 17:03 Cole Murray Whether through CLI, MCPs, other tools, you can then hook that into your production systems, primarily for like SRE type use cases, but you are not necessarily like trying to test your prod internal microservice through the system.
- ▶ 28:18 Walden Yan The thing we found is, so like MCPs, um, obviously it has been like, it's like really big explosion of, oh, you can go like integrate it with all these different things. 8 times in the scene
- ▶ 39:45 Walden Yan We've actually given Devon an MCP so they can just go arbitrarily message other Devons and create new Devons, et cetera.
AI Agents Need Computers: 74% MoM Growth, 850K/Day Runs, & New Agent Cloud — Ivan Burazin, Daytona
- ▶ 44:31 Shawn Wang I'm just kind of going through like the mental list of things that are in your favor, which is for example, MCP versus CLI. 2 times in the scene
⚡️ How to turn Documents into Knowledge: Graphs in Modern AI — Emil Eifrem, CEO Neo4J
- ▶ 24:00 Emil Eifrem Um, people don't talk about this, but like actually the initial MCP release includes like a tiny little in memory graph database.
Notion’s Sarah Sachs & Simon Last on Custom Agents, Evals, and the Future of Work
- ▶ 0:03 Simon Last I'm still bullish on MCPs in, in a certain environment. 6 times in the scene
- ▶ 41:11 Shawn Wang Talking about integrations, you prompted me, so I got to ask MCP, CLI, what's going on? 8 times in the scene
- ▶ 43:50 Sarah Sachs So we will always support our MCP insofar as other people are using MCPs, right? 5 times in the scene
- ▶ 49:04 Simon Last So, so we have like a tool integration abstraction, for example, and then MCP is like a type of integration.
Extreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI
- ▶ 38:29 Ryan Lopopolo Uh, there was one point where we had wired Playwright directly up to the Electron app, uh, with MCP. 2 times in the scene
- ▶ 49:54 unnamed speaker Integration layer, MCP is dead.
Marc Andreessen introspects on Death of the Browser, Pi + OpenClaw, and Why "This Time Is Different"
- ▶ 37:25 Marc Andreessen And so like this whole idea where we need like MCP and these like products, fancy protocols, whatever.
Anthropic’s Felix Rieseberg on AI Coworkers, Local-First Agents, and the Future of Knowledge Work
- ▶ 9:00 Alessio Fanelli You have obviously MCPs, you have skills, you have like, obviously the models, which is a big part.
- ▶ 14:40 Felix Rieseberg You're noticing that a lot of people, especially as the models get better, a lot of people throw up their hands when it comes to MCP connectors and they say, I'm not gonna, I'm not gonna go through like 4 times in the scene
- ▶ 25:50 Felix Rieseberg And you can kind of, kind of already see this in like skills and NTP servers, right? 3 times in the scene
- ▶ 38:25 Alessio Fanelli I think with MCPs, people do the same thing.
⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic
- ▶ 1:55 Samuel Colvin I don't think we've done anything particularly special in our MCP server, but because the AI can just go write SQL, it's way more powerful than I think on many platforms.
- ▶ 3:42 Samuel Colvin Uh, using code to call MCP servers.
- ▶ 29:50 Samuel Colvin So basically you can define an agent entirely in a TOML file, everything from the model to the system prompt to all of the capabilities, whether they be code mode or compaction or registering an MCP server. 3 times in the scene
⚡️ OpenClaw's Memory Sucks and the fix is simple — Dhravya Shah, Supermemory
- ▶ 0:59 Dhravya Shah So we had an NCP launch, and then we had another launch for the app itself. 3 times in the scene
Agent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup
- ▶ 1:10:08 Kyle Kranen You could still do it by API, but like, there's this highlighting of like, what is the difference between like a CLI and an MCP, right?
Brex’s AI Hail Mary — With CTO James Reggio (acquired for $5B by Capital One!)
- ▶ 11:43 Alessio Fanelli We'll put the diagram in the video where you had the LLM gateway, you have like the whole MCP layer. 2 times in the scene
- ▶ 20:32 Alessio Fanelli What about MCPs as like sub agents? 2 times in the scene
Artificial Analysis: The Independent LLM Analysis House — with George Cameron and Micah Hill-Smith
- ▶ 47:48 Micah Hill-Smith Based on it, the things that, like, I find most impressive currently that I am somewhat surprised work really well in late 25 are that I can have models use Superbase MCP to read only, of course, run a whole bunch of SQL queries to do…