I spent a week building Wingman , an open source MCP server that renders a persistent task panel inline in Claude conversations using MCP Apps (SEP-1865). The spec is solid. The SDK is solid. But I hit two bugs that cost me most of a weekend each, and neither is documented anywhere I could find. Writing them up here in case they save someone else the time. Bug 1: resourceUri has two valid-looking locations, and only one works MCP Apps needs a way to tell the host "render this resource as a UI for this tool call." That pointer lives in _meta.ui.resourceUri . The question is: meta on what? I started with a parameterized resource template, ui://wingman/panel/{plan_name} , registered per plan. That was my first mistake. Parameterized templates get listed under resources/templates/list , not resources/list , and hosts do not prefetch or render anything from the templates list. The fix was straightforward once I found it: register one static resource, ui://wingman/panel , and pass the actual plan data through structuredContent on the tool result instead of baking it into the URI. That fix surfaced the real bug. My show_plan tool was returning a plain Python dict: return { " plan " : plan_data , " _meta " : { " ui " : { " resourceUri " : " ui://wingman/panel " }} } This looks correct. It is not. FastMCP's result conversion takes a returned dict and serializes the whole thing into structuredContent , verbatim, including any _meta key the dict happens to carry. So the actual wire result looked like this: result . structuredContent [ " _meta " ][ " ui " ][ " resourceUri " ] # == "ui://wingman/panel", but wrong place result . meta # None — this is what the host actually reads MCP Apps hosts read resourceUri off the top-level _meta on the CallToolResult , not off whatever ended up inside structuredContent . With that pointer effectively missing, the host had nowhere to bind the iframe. The visible symptom was strange: actions in the UI would update on screen but nothing persist

Built a small tool for Claude Code that tracks whether “agent memory” rules actually pay for themselves in token usage. The idea is simple: every persistent instruction should justify itself by reducing future token cost. If it doesn’t, it gets flagged for removal. Over time, a surprising amount of memory ends up being neutral or negative ROI once measured. Check it out, would mean a lot :) Repo: https://github.com/vukkt/token-warden

The move comes after the company left potentially sensitive data from the initiative exposed internally.

CDN and Node package to generate ASCII graphs inline Discussion | Link

Valve's Steam Machine finally has a price: a whopping $1,049 for the 512GB configuration or $1,349 for the 2TB version. And those are without bundled controllers, which drive up the cost more. The prices are so high in part because Valve isn't subsidizing the hardware, and the company has already indicated that the component crisis […]

He had retinal tears and bruises from squishing his eyeballs with the gun.

Article URL: https://www.ycombinator.com/companies/kyber/jobs/FGmI8mx-head-of-engineering Comments URL: https://news.ycombinator.com/item?id=48636125 Points: 0 # Comments: 0

The loop takes agentic AI a step further by authorizing a swarm of agents to work continuously in the background, endlessly.

Microsoft inked a 20-year power purchase agreement with Chevron, locking in decades of carbon emissions from a new natural gas power plant.

Employees had previously raised concerns about the initiative, which involves collecting workers’ keystroke data to train AI models.

Spoiler: It's more Siri stuff.

New way for you & agents to search for businesses on Stripe Discussion | Link

What does an AI company do after one of those not-acqui-hire deals? Groq raised money, is leaning into its neocloud business, and is hiring new execs.

"Winning" bets were made on cloned website and would have lost money, WSJ finds.