# Rebuilding the web for agents — Liad Yosef, MCP Apps

Source: [AI Engineer](https://www.youtube.com/watch?v=waI44NP1abk)  
Feed7 permalink: https://feed7.dev/p/rebuilding-the-web-for-agents-liad-yosef-mcp-apps-0c3fgjh  
Published: 2026-09-16T14:30:03.000Z  
Trust: Source Linked (source_linked)

## Why Included

Publishing agent instructions is not enough: tested agents mostly ignored llms.txt and navigated documentation directly, so agent readiness needs observed journey testing and discoverable interfaces.

## Source Summary

Aura found that **almost 50% of tested sites** published llms.txt, yet almost none of the tested agents used it without another page pointing them there. Agents generally went first to documentation and then the homepage.

## Practical Implication

Test real tasks across several agent harnesses and inspect their paths instead of treating one metadata file as compliance. Expose callable resources through standards such as **MCP Apps** and **AI catalog.json**, while retaining UI for choices that still require human judgment.

## Agent-Ready Context

Aura found that **almost 50% of tested sites** published llms.txt, yet almost none of the tested agents used it without another page pointing them there. Agents generally went first to documentation and then the homepage.

Test real tasks across several agent harnesses and inspect their paths instead of treating one metadata file as compliance. Expose callable resources through standards such as **MCP Apps** and **AI catalog.json**, while retaining UI for choices that still require human judgment.

The findings come from Aura’s own scans and journey tooling; the talk does not disclose the sampled sites, agents, or scoring method in enough detail for independent comparison. The broader prediction of a nearly headless web is directional, not established.

## Connected Context

Feed7 judgment across 807 accumulated Signals:

This narrows agent-ready web design: publishing agent metadata is ineffective if harnesses do not discover or consult it. The practical requirement becomes journey testing across agents plus callable, standardized resources, with UI preserved where people must judge choices. It shifts emphasis from nominal compliance to observed access paths, while leaving the headless-web prediction unproven.

- [MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef](https://feed7.dev/p/mcp-apps-extending-the-frontier-ido-salomon-liad-yosef-1gtlsr9) — MCP Apps supplies the concrete host-governed UI mechanism for the Signal’s recommendation to expose callable resources without removing human-facing controls.
- [ChromeDevTools/chrome-devtools-mcp](https://feed7.dev/p/chrome-devtools-mcp-0ow49x2) — Chrome DevTools MCP provides the runtime evidence needed to inspect real agent journeys—navigation, network activity, console output, and screenshots—instead of assuming an agent-facing file is discovered.
- [The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans — Corey Gallon, Rexmore](https://feed7.dev/p/the-dark-arts-of-web-automation-teaching-agents-to-use-websites-like-hum-12nj0e0) — Browser agents can still traverse conventional sites through verified sense-act loops; this Signal argues that standardized callable resources can reduce dependence on such brittle navigation while retaining UI for judgment-heavy steps.
- [Latest MCP spec now supported in mcp-handler](https://feed7.dev/p/latest-mcp-spec-now-supported-in-mcp-handler-1kkt3s0) — Adopting MCP as an agent-facing access layer creates an implementation consequence: servers must account for current transport, runtime, and SDK compatibility rather than treating protocol publication alone as sufficient.

## Context Map

- Layer: context
- Domains: coding
- Topics: mcp, tool-use, computer-use

## Uncertainty

- The findings come from Aura’s own scans and journey tooling; the talk does not disclose the sampled sites, agents, or scoring method in enough detail for independent comparison. The broader prediction of a nearly headless web is directional, not established.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.