Model Context Protocol
Overview
Model Context Protocol, or MCP, is a standard pattern for connecting AI applications to tools, data, and interactive capabilities through structured servers and clients. In this wiki it also includes MCP Apps and agent-facing interfaces that expose richer actions or UI surfaces to models.
Conference Context
MCP emerged from the need to standardize how AI clients discover and call tools, access resources, and integrate with external systems. It sits in the lineage of plugin APIs, language-server style tooling, RPC, browser extensions, and developer-tool protocols.
Significance
Agents are only as useful as the tools and context they can safely access. MCP reduces one-off integrations, gives tool providers a common surface, and helps clients reason about capabilities, permissions, and interaction patterns.
Applied Use
Define focused MCP servers with clear tools, schemas, resources, and permission boundaries. Keep tool names concrete, return structured results, test with inspectors, and design for least privilege. For MCP Apps, treat UI and iframe boundaries as part of the security and product contract.
MCP is useful in IDEs, desktop assistants, enterprise data connectors, browser agents, design tools, developer platforms, and internal operations systems.
Use MCP when multiple AI clients need access to the same tools or when a tool provider wants a standard agent-facing integration. For a single narrow app, direct APIs may be simpler until reuse or interoperability matters.
Define focused MCP servers with clear tools, schemas, resources, and permission boundaries. Keep tool names concrete, return structured results, test with inspectors, and design for least privilege. For MCP Apps, treat UI and iframe boundaries as part of the security and product contract.
MCP is useful in IDEs, desktop assistants, enterprise data connectors, browser agents, design tools, developer platforms, and internal operations systems.
Use MCP when multiple AI clients need access to the same tools or when a tool provider wants a standard agent-facing integration. For a single narrow app, direct APIs may be simpler until reuse or interoperability matters.
Define focused MCP servers with clear tools, schemas, resources, and permission boundaries. Keep tool names concrete, return structured results, test with inspectors, and design for least privilege. For MCP Apps, treat UI and iframe boundaries as part of the security and product contract.
MCP is useful in IDEs, desktop assistants, enterprise data connectors, browser agents, design tools, developer platforms, and internal operations systems.
Use MCP when multiple AI clients need access to the same tools or when a tool provider wants a standard agent-facing integration. For a single narrow app, direct APIs may be simpler until reuse or interoperability matters.
Define focused MCP servers with clear tools, schemas, resources, and permission boundaries. Keep tool names concrete, return structured results, test with inspectors, and design for least privilege. For MCP Apps, treat UI and iframe boundaries as part of the security and product contract.
MCP is useful in IDEs, desktop assistants, enterprise data connectors, browser agents, design tools, developer platforms, and internal operations systems.
Use MCP when multiple AI clients need access to the same tools or when a tool provider wants a standard agent-facing integration. For a single narrow app, direct APIs may be simpler until reuse or interoperability matters.
Define focused MCP servers with clear tools, schemas, resources, and permission boundaries. Keep tool names concrete, return structured results, test with inspectors, and design for least privilege. For MCP Apps, treat UI and iframe boundaries as part of the security and product contract.
MCP is useful in IDEs, desktop assistants, enterprise data connectors, browser agents, design tools, developer platforms, and internal operations systems.
Use MCP when multiple AI clients need access to the same tools or when a tool provider wants a standard agent-facing integration. For a single narrow app, direct APIs may be simpler until reuse or interoperability matters.
Define focused MCP servers with clear tools, schemas, resources, and permission boundaries. Keep tool names concrete, return structured results, test with inspectors, and design for least privilege. For MCP Apps, treat UI and iframe boundaries as part of the security and product contract.
MCP is useful in IDEs, desktop assistants, enterprise data connectors, browser agents, design tools, developer platforms, and internal operations systems.
Use MCP when multiple AI clients need access to the same tools or when a tool provider wants a standard agent-facing integration. For a single narrow app, direct APIs may be simpler until reuse or interoperability matters.
Connections
- 2026 07 01 jan curn mcp doesn t suck your agent does — MCP doesn’t suck — your agent does; Jan Curn (Day 4 — Session Day 3 · 1:55pm-2:15pm · Expo Stage 2 NW; official schedule)
- 2026 06 30 liad yosef mcp apps extending the frontier — MCP Apps - Extending the frontier; Liad Yosef, Ido Salomon (Day 3 — Session Day 2 · 2:25pm-2:45pm · Context Engineering; verified event YouTube resource; via youtube o zkvb0iFDQ)
- 2026 06 30 dustin mihalik mcp apps give the model data give the user a ui — MCP Apps: Give the Model Data, Give the User a UI; Dustin Mihalik (Day 3 — Session Day 2 · 2:50pm-3:10pm · Context Engineering; official schedule)
- 2026 06 30 averi kitsch build time vs run time why your dev tools will fail in production — Build-Time vs. Run-Time: Why Your Dev Tools Will Fail in Production; Averi Kitsch, Prerna Kakkar (Day 3 — Session Day 2 · 10:45am-11:05am · Context Engineering; official schedule)
- 2026 06 29 jim clark who approved that mcp server governing the tool layer — Who Approved That MCP Server? Governing the Tool Layer; Jim Clark (Day 2 — Session Day 1 · 1:55pm-2:15pm · Expo Stage 1 NE; official schedule)
- 2026 06 29 dan adler the enterprise agentic gap when developer level ai tools hit millions of lines — The Enterprise Agentic Gap: When Developer-Level AI Tools Hit Millions of Lines; Dan Adler (Day 2 — Session Day 1 · 10:45am-11:05am · Expo Stage 2 NW; official schedule)
- 2026 06 29 jesse lumarie building the engine while flying the plane launching the figma mcp server — Building the engine while flying the plane — launching the Figma MCP server; Jesse Lumarie (Day 2 — Session Day 1 · 11:10am-11:30am · AI-Native Enterprises; official schedule)
- 2026 06 30 cornelia davis mcp tasks async why the heck aren t any agents supporting mcp tasks async — MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?; Cornelia Davis (Day 3 — Session Day 2 · 3:20pm-3:40pm · Context Engineering; official schedule)
- 2026 07 01 sandhya subramani agents that forge their own tools self modifying ai in the wild — Agents That Forge Their Own Tools: Self-Modifying AI in the Wild; Sandhya Subramani (Day 4 — Session Day 3 · 12:05pm-12:25pm · Expo Stage 4 SE; official schedule)
- 2026 06 29 alexander embiricos the golden age of ai engineering — The Golden Age of AI Engineering; Alexander Embiricos, Romain Huet (Day 2 — Session Day 1 · 9:25am-9:45am · Software Factories; verified event YouTube resource; via youtube pMggiOb18tc)
- 2026 06 29 mark lummus burn your flags how paypal designs interactive cli tools for agents — Burn your flags: How PayPal designs interactive CLI tools for agents; Mark Lummus, Navinkumar Patil (Day 1 — Workshop Day · 2:20pm-4:20pm · Workshops Day 1; official schedule)
- 2026 07 01 nikita kothari mcps clis and skills choosing the right tooling layer for agentic development — MCPs, CLIs, and Skills: Choosing the Right Tooling Layer for Agentic Development; Nikita Kothari (Day 4 — Session Day 3 · 11:10am-11:30am · Agentic Engineering; official schedule)
- 2026 06 29 ethan jung min cha dual surface architecture serving humans and agents from the same tool layer — Dual-Surface Architecture: Serving Humans and Agents from the Same Tool Layer; Ethan (Jung Min) Cha (Day 2 — Session Day 1 · 1:55pm-2:15pm · Security; official schedule)
- 2026 06 29 pedro lopez how we built the airbyte agent mcp server and cli — How We Built the Airbyte Agent MCP Server and CLI; Pedro Lopez (Day 2 — Session Day 1 · 3:45pm-4:05pm · Expo Stage 1; official schedule)
- 2026 06 30 thorsten hans edge native ai building ultra fast agents and mcp servers with spin — Edge-Native AI: Building Ultra-Fast Agents and MCP Servers with Spin; Thorsten Hans (Day 3 — Session Day 2 · 1:55pm-2:15pm · Expo Stage 2; official schedule)
- 2026 06 29 maria bledsoe using ai tools to teach old apps new tricks — Using AI tools to teach old apps new tricks; Maria Bledsoe (Day 2 — Session Day 1 · 2:25pm-2:45pm · Track M; official schedule)
- 2026 07 01 anil nadiminti when ai agents pay and sellers monetize building x402 apps for agentic commerce on aws — When AI Agents Pay and Sellers Monetize: Building x402 Apps for Agentic Commerce on AWS; Anil Nadiminti (Day 4 — Session Day 3 · 11:40am-12:00pm · Agentic Commerce; official schedule)
- 2026 06 29 merve noyan skill issue stop deploying vision language models use them with skills to build e2e vision apps on edge — Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge; Merve Noyan (Day 2 — Session Day 1 · 11:40am-12:00pm · Vision & OCR; official schedule)
- 2026 06 29 vasuman moza ai tools for forward deployed engineering — AI tools for Forward Deployed Engineering; Vasuman Moza (Day 2 — Session Day 1 · 11:40am-12:00pm · Forward Deployed Engineering; official schedule)
- 2026 06 29 will brown the prime intellect stack — The Prime Intellect Stack; Will Brown (Day 1 — Workshop Day · 4:30pm-5:30pm · Workshops Day 1; verified event YouTube resource; via youtube V EDrhIhHzQ)
- 2026 06 29 pamela fox get started with models in microsoft foundry to build ai apps — Get Started with Models in Microsoft Foundry to Build AI Apps; Pamela Fox (Day 1 — Workshop Day · 9:00am-10:15am · Track M; official schedule)
- 2026 06 30 ashu joshi deploy agents to users in m365 teams and apps — Deploy agents to users in M365, Teams, and apps; Ashu Joshi (Day 3 — Session Day 2 · 3:20pm-3:40pm · Track M; official schedule)
- 2026 06 29 lee robinson recursive model improvement — Recursive Model Improvement; Lee Robinson (Day 2 — Session Day 1 · 5:10pm-5:30pm · Software Factories; verified event YouTube resource; via youtube q4Tr DknG2M)
- 2026 06 30 thariq shihipar field guide to fable — Field Guide to Fable; Thariq Shihipar (Day 3 — Session Day 2 · 9:05am-9:25am · Autoresearch; verified event YouTube resource; via youtube 9fubhllmsBU)
- John Craft
- Pamela Fox
- Sandhya Subramani
- Jason Liu
- John Lindquist
- Liad Yosef
- Frank Coyle
- Charlie Guo
- Merve Noyan
- Arun Sekhar
- Elizabeth Fuentes Leone
- Harshul Jain
- Tanmay Sah
- Kwindla Kramer
- Jan Curn
- Ido Salomon
- Dustin Mihalik
- Averi Kitsch
- Prerna Kakkar
- Jim Clark
- Dan Adler
- Jesse Lumarie
- Cornelia Davis
- Alexander Embiricos
- Microsoft
- OpenAI
- Docker
- Amazon Web Services
- Hugging Face
- NVIDIA
- MCP Apps
- PayPal
- Towards AI
- Uber
- Warp
- Weights & Biases by CoreWeave
- egghead.io
- Sourcegraph
- UCAL Berkeley
- Nubank
- Navan
- 2026 06 30 geoffrey litt understanding is the new bottleneck — Understanding is the new bottleneck; Geoffrey Litt (Day 3 — Session Day 2 · 10:45am-11:05am · Design Engineering; verified event YouTube resource; via youtube WkBPX oDMnA)
- 2026 06 29 liad yosef rebuilding the web for agents — Rebuilding the web for agents; Liad Yosef (Day 2 — Session Day 1 · 12:05pm-12:25pm · Search & Retrieval; official schedule)
- 2026 06 30 corey gallon the dark arts of web automation teaching agents to use websites like humans — The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans; Corey Gallon (Day 3 — Session Day 2 · 12:05pm-12:25pm · Computer Use; official schedule)
- 2026 06 30 liad yosef mcp apps extending the frontier — MCP Apps - Extending the frontier; Liad Yosef, Ido Salomon (Day 3 — Session Day 2 · 2:25pm-2:45pm · Context Engineering; related YouTube resource; via youtube o zkvb0iFDQ)
- 2026 06 29 kwindla kramer the new primitives building ai native software — The New Primitives: Building AI-Native Software; Kwindla Kramer (Day 2 — Session Day 1 · 10:45am-11:05am · Voice & Realtime AI; related YouTube resource; via youtube sAOBXCDiDOs)
- 2026 06 29 pedro lopez how we built the airbyte agent mcp server and cli — How We Built the Airbyte Agent MCP Server and CLI; Pedro Lopez (Day 2 — Session Day 1 · 3:45pm-4:05pm · Expo Stage 1; related YouTube resource; via youtube sAOBXCDiDOs)
- 2026 06 30 joseph wang emulated the data for fully autonomous software engineers and companies — Emulated: The data for fully autonomous software engineers and companies; Joseph Wang (Day 3 — Session Day 2 · 1:55pm-2:15pm · Posttraining & Midtraining; related YouTube resource; via youtube sAOBXCDiDOs)
- 2026 06 29 liad yosef rebuilding the web for agents — Rebuilding the web for agents; Liad Yosef (Day 2 — Session Day 1 · 12:05pm-12:25pm · Search & Retrieval; related YouTube resource; via youtube o zkvb0iFDQ)
- 2026 06 29 ido salomon we re the bottleneck but we don t have to be — We're the bottleneck, but we don't have to be; Ido Salomon (Day 2 — Session Day 1 · 2:25pm-2:45pm · Software Factories; related YouTube resource; via youtube o zkvb0iFDQ)
- 2026 06 29 alexander embiricos the golden age of ai engineering — The Golden Age of AI Engineering; Alexander Embiricos, Romain Huet (Day 2 — Session Day 1 · 9:25am-9:45am · Software Factories; related YouTube resource; via youtube pMggiOb18tc)
- youtube 2e9ANoOEn28 slides — What if the harness mattered more than the model? - Aditya Bhargava, Etsy (8 extracted slide frames)
- youtube sAOBXCDiDOs slides — MCP Apps: Primitives, discovery, and the Future of Software - Pietro Zullo, Manufact, Inc (18 extracted slide frames)
- 2026 06 30 liad yosef mcp apps extending the frontier — MCP Apps - Extending the frontier; Liad Yosef, Ido Salomon (Day 3 — Session Day 2 · 2:25pm-2:45pm · Context Engineering; official schedule)
- 2026 07 01 rafael levi video discovery for agentic world model training — Video Discovery for Agentic World-Model Training; Rafael Levi (Day 2 — Session Day 1 · 2:50pm-3:10pm · Expo Stage 2 NW; related YouTube resource; via youtube btxGmN8RvNU)
- 2026 06 29 du an lightfoot agents that own their inference building production ai agents on dedicated gpus — Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs; Du'an Lightfoot (Day 1 — Workshop Day · 9:00am-11:00am · Track 7; related YouTube resource; via youtube wFTVEDYVJT0)
Evidence Graph
Transcript-backed resources
- youtube o zkvb0iFDQ — MCP UI: Extending the frontier — Liad Yosef and Ido Salomon, MCP Apps
- youtube V EDrhIhHzQ — The Prime Intellect Stack — Will Brown, Prime Intellect
- youtube q4Tr DknG2M — Recursive Model Improvement — Lee Robinson, Cursor, SpaceXAI
- youtube pMggiOb18tc — The Golden Age of AI Engineering — Alexander Embiricos & Romain Huet & Peter Steinberger, OpenAI
- youtube 9fubhllmsBU — Field Guide to Fable — Thariq Shihipar, Anthropic
- youtube 4sX_He5c4sI — WF2026: Autoresearch & Keynotes ft. Anthropic, Google DeepMind, Amazon AGI, Sonar, Arena, Recursive
- youtube WkBPX oDMnA — Understanding is the new bottleneck — Geoffrey Litt, Notion
Quote signals
- “In this case it decides to actually call the server tool but the control is in the hands of the host and everything stays in context.” — youtube o zkvb0iFDQ
- “And just a few months back MCPUI we partnered with Anthropic and OpenAI to really put this into the MCP standard as the first official extension called MCP apps.” — youtube o zkvb0iFDQ
- “Obviously shout out Postman and Goose and Claude the first one that released Claude apps that actually supported MCP apps.” — youtube o zkvb0iFDQ
- “Um and to give people an option to not just use the open-source models that are getting quite good, but to take them and make them even better on their own use cases.” — youtube V EDrhIhHzQ
- “People talk about environment in the context of RL and they think of like RL environments, but environments are more than just for RL.” — youtube V EDrhIhHzQ
- “And our goal is to just make this a really flexible toolkit for all the kinds of evaluation things people want to do both for API models as well as for post training.” — youtube V EDrhIhHzQ
Transcript-backed resources
Quote signals
Transcript-backed resources
Quote signals
Transcript-backed resources
Quote signals
Transcript-backed resources
- youtube sAOBXCDiDOs — MCP Apps: Primitives, discovery, and the Future of Software - Pietro Zullo, Manufact, Inc
- youtube vh2VGuQ3zhY — The 100-Tool Agent Is a Trap - Sohail Shaikh & Ankush Rastogi, Prosodica
- youtube _xIwFcnHqp4 — Building Interactive UIs in VS Code with MCP Apps — Marlene Mhangami & Liam Hampton, GitHub
- youtube ghJmWQCIHRM — The agent-ready web: Simplify user actions with WebMCP — Tara Agyemang, Google
- youtube _B4Pv9ttFgY — Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents — Michael Hablich, Google
- youtube 1IdzkRVmWAA — How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI
- youtube HsxQICTLF84 — Building an ACP-Compatible Agent Live — Bennet Fenner, Zed
- youtube c 2eEv2ou7Y — Why MCP and ChatGPT Apps Use Double Iframes — Frédéric Barthelet, Alpic
- youtube HEFSExa0xl0 — Teaching Coding Agents to do Spreadsheets - Nuno Campos, Witan Labs
- youtube spNAUEgq_A8 — The Future Is Domain-Specific Agents - Justin Schroeder, StandardAgents
- youtube 2e9ANoOEn28 — What if the harness mattered more than the model? - Aditya Bhargava, Etsy
- youtube UcYoMg 8 L8 — 500 people vibe-coded for 30 days. I was one of them. - Sanja Grbic, Automattic
- youtube G6IlDzj8OjA — GTM Is You - Victoria Melnikova, Evil Martians
- youtube xUnRQ9vLXxo — What do we build now? — @t3dotgg
- youtube hCMrEfPG2Yg — Beyond Components: Designing Generative UI for MCP Apps — Ruben Casas, Postman
- youtube BqZrTdgBaPw — Running a Chess YouTube Channel entirely by AI — Stephan Steinfurt, TNG
- youtube 4uFVSLgD2Q4 — Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov
Quote signals
- “I'm an engineer here at OpenGov and today we're going to be talking about agents in production, specifically how OpenGov built and scaled OG Assist.” — youtube 4uFVSLgD2Q4
- “So, that's kind of how we handled long context and memory, and it's worked pretty well for us.” — youtube 4uFVSLgD2Q4
- “Uh it's an open source inspector, again, uh something comparable to the official inspector from the model context protocol maintainers that allows you to test these MCP servers and apps specifically uh on your local machine.” — youtube sAOBXCDiDOs
- “MCP apps is now the official extension of the Model Context Protocol that allows to return UI elements within MCP servers.” — youtube sAOBXCDiDOs
- “[clears throat] And also Cursor allows you to submit their MCP server set uh The way you submit is different for all three, but basically what happens is that you need to make sure that your MCP app is compliant.” — youtube sAOBXCDiDOs
- “The let's say past few decades, we have been building the web for human actions and human eyes, and we've been trying to optimize for that, but these days, it's not just humans that are using the web.” — youtube ghJmWQCIHRM
- “Well, today I'm going to share four engineering lessons from the Chrome uh DevTools team on how we build Chrome DevTools for agents and how we deployed it for effect.” — youtube _B4Pv9ttFgY
- “In a world where you are delegating away work to agents and automating away agents, you need to think about trust boundaries.” — youtube _B4Pv9ttFgY
Transcript-backed resources
- youtube btxGmN8RvNU — Your Agent's Biggest Lie: "I Searched the Web" — Rafael Levi, Bright Data
Quote signals
This evidence graph consolidates scheduled talks, linked videos, transcripts, and slide-derived material connected to this topic.
Linked Sessions
- MCP doesn’t suck — your agent does
- MCP Apps - Extending the frontier
- MCP Apps: Give the Model Data, Give the User a UI
- The New Primitives: Building AI-Native Software
- How We Built the Airbyte Agent MCP Server and CLI
- Emulated: The data for fully autonomous software engineers and companies
- Build-Time vs. Run-Time: Why Your Dev Tools Will Fail in Production
- Who Approved That MCP Server? Governing the Tool Layer
- The Enterprise Agentic Gap: When Developer-Level AI Tools Hit Millions of Lines
- Building the engine while flying the plane — launching the Figma MCP server
Media Signals
youtube-blW-lSd5CYQ— 9 slide-derived text signals- Slide-derived themes for
youtube-blW-lSd5CYQ: google, maps, intelligence, emerge, runs, actors, compass, data. - Evidence links for
youtube-blW-lSd5CYQ: youtube blW lSd5CYQ, youtube blW lSd5CYQ slides, youtube blW lSd5CYQ dense slides, youtube blW lSd5CYQ reconstructed slides youtube-o-zkvb0iFDQ— 3,969 transcript words; 1 slide-derived text signals- Transcript signals for
youtube-o-zkvb0iFDQ: apps, host, claude, back, chatgpt, look, mcpui, chat. - Slide-derived themes for
youtube-o-zkvb0iFDQ: engineering, future. - Evidence links for
youtube-o-zkvb0iFDQ: youtube o zkvb0iFDQ, youtube o zkvb0iFDQ transcript, youtube o zkvb0iFDQ slides, youtube o zkvb0iFDQ dense slides, youtube o zkvb0iFDQ reconstructed slides youtube-E71YtNbCFXY— 5 slide-derived text signals- Slide-derived themes for
youtube-E71YtNbCFXY: pelt, remember, connections. - Evidence links for
youtube-E71YtNbCFXY: youtube E71YtNbCFXY, youtube E71YtNbCFXY slides, youtube E71YtNbCFXY dense slides, youtube E71YtNbCFXY reconstructed slides
Source Coverage
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
| Evidence type | Count | Review note |
| --- | ---: | --- |
| other | 53 | Related pages outside the main evidence categories. |
| resources | 22 | Video/resource pages; check source status before treating as primary event evidence. |
| slides | 11 | OCR or reconstructed slide evidence; mark claims as OCR-derived unless image-reviewed. |
| talks | 24 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
| tools | 3 | Derived inventory pages; use as entity context, not independent proof. |
| transcripts | 1 | Transcript markdown; check session matching and caption quality. |
Talks
- 2026 07 01 jan curn mcp doesn t suck your agent does
- 2026 06 30 liad yosef mcp apps extending the frontier
- 2026 06 30 dustin mihalik mcp apps give the model data give the user a ui
- 2026 06 29 kwindla kramer the new primitives building ai native software
- 2026 06 29 pedro lopez how we built the airbyte agent mcp server and cli
- 2026 06 30 joseph wang emulated the data for fully autonomous software engineers and companies
Resources
- youtube sAOBXCDiDOs
- youtube btxGmN8RvNU
- youtube wFTVEDYVJT0
- youtube vh2VGuQ3zhY
- youtube _xIwFcnHqp4
- youtube ghJmWQCIHRM
Slides
- youtube 2e9ANoOEn28 slides
- youtube sAOBXCDiDOs slides
- youtube blW lSd5CYQ slides
- youtube blW lSd5CYQ dense slides
- youtube blW lSd5CYQ reconstructed slides
- youtube o zkvb0iFDQ slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
| other | 55 | Related pages outside the main evidence categories. |
| resources | 23 | Video/resource pages; check source status before treating as primary event evidence. |
| talks | 27 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
Talks
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
| other | 61 | Related pages outside the main evidence categories. |
| resources | 25 | Video/resource pages; check source status before treating as primary event evidence. |
| talks | 29 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
Talks
- 2026 06 30 averi kitsch build time vs run time why your dev tools will fail in production
- 2026 06 29 jim clark who approved that mcp server governing the tool layer
- 2026 06 29 dan adler the enterprise agentic gap when developer level ai tools hit millions of lines
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
Talks
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
Talks
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
Talks
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
| other | 62 | Related pages outside the main evidence categories. |
| resources | 26 | Video/resource pages; check source status before treating as primary event evidence. |
| talks | 30 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
Talks
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
| other | 63 | Related pages outside the main evidence categories. |
| resources | 27 | Video/resource pages; check source status before treating as primary event evidence. |
| talks | 31 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
Talks
Resources
Slides
Transcripts
Tools
This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.
| other | 64 | Related pages outside the main evidence categories. |
| resources | 28 | Video/resource pages; check source status before treating as primary event evidence. |
| talks | 32 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
Talks
Resources
Slides
Transcripts
Tools
Active Use Cases
- Connecting agents to repositories, browsers, docs, databases, and SaaS tools.
- MCP Apps that return interactive UI from tool servers.
- Agent-ready web and developer-tool integrations.
- Local inspectors and compliance checks for tool servers.