Hacker News: HotHotLava

Show HN: Withmcp – A quick, system-wide MCP toggle

HotHotLava — Sat, 26 Sep 2026 22:35:04 +0000

MCP seem to be going out of fashion, but for many authenticated services it still seems to be the easiest and most straightforward way to interact with the system, in particular if you don't want credentials to be on the same host as the agent.

However, the most popular harnesses have really rudimentary MCP support. For example, Claude Code has no way to temporarily disable a configured server.

So I built this tool, a custom harness launcher that can be used to configure an MCP for any service that looks halfway interesting, without wasting your context window and attention budget with warnings about expired logins etc.

Comments URL: https://news.ycombinator.com/item?id=49861216

Points: 1

# Comments: 0

New comment by HotHotLava in "Claude Code reads AGENTS.md only when telemetry is on [fixed]"

HotHotLava — Wed, 23 Sep 2026 13:39:32 +0000

"extremely severe" - aren't we laying it on a bit thick here? The whole impact seems to be that users who have telemetry turned off got this feature ~2 days later, when the bug was noticed.

New comment by HotHotLava in "Navier-Stokes Announcement"

HotHotLava — Sun, 13 Sep 2026 02:09:54 +0000

Per the rules link that you yourself post, no, publication must not necessarily happen in a peer-reviewed journal.

New comment by HotHotLava in "Navier-Stokes Announcement"

HotHotLava — Sun, 13 Sep 2026 01:57:49 +0000

Take a look at https://github.com/leanprover/comparator which was used to verify the result. It's of course not impossible that they're hitting some bug, but way harder than one would intuitively think. For starters, they'd have to hit two bugs in two independently written Lean kernels.

New comment by HotHotLava in "Navier-Stokes Announcement"

HotHotLava — Sat, 12 Sep 2026 21:44:40 +0000

In what world is peer review a higher standard than formal verification in Lean?

Not in the world mathematicians have been living in for the past decades at least. Nearly all big theorems that have been formalized so far had been published beforehand, and it was usually regarded as a step up in rigor. Wrong results get published in peer reviewed journals all the time.

New comment by HotHotLava in "Navier-Stokes – Tristan Buckmaster [pdf]"

HotHotLava — Tue, 08 Sep 2026 22:15:43 +0000

I feel like there's a pretty huge difference between using inputs and outputs as part of a general training corpus, and looking at a specific users workspace after hearing rumours and yoinking their ideas to beat them to the point.

Unless OpenAI finished a whole new training run on the latest data in the last few days, the possible allegation seems to be the latter.

New comment by HotHotLava in "Formalizing Fermat's Last Theorem"

HotHotLava — Fri, 04 Sep 2026 19:47:36 +0000

The nice thing is, once all of these proofs are formalized in a machine-checkable language, it should be relatively straightforward to translate the corpus between different languages, if someone finds something with a nicer syntax.

New comment by HotHotLava in "Kimi K3: Open Frontier Intelligence"

HotHotLava — Fri, 17 Jul 2026 09:40:32 +0000

What would be "noise" in this context? Random words, random sentences, random complete short stories?

New comment by HotHotLava in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

HotHotLava — Sat, 13 Jun 2026 10:20:45 +0000

How do you "easy" VPN into the US in 1995? The whole consumer VPN industry didn't exist back then.

New comment by HotHotLava in "Using “underdrawings” for accurate text and numbers"

HotHotLava — Mon, 04 May 2026 10:04:16 +0000

I think you're vastly overestimating the average persons ability to use Blender if you can do that in an afternoon; just figuring out how to place a colored cube and the camera probably takes an afternoon if you pick up Blender for the first time.

New comment by HotHotLava in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

HotHotLava — Wed, 22 Apr 2026 16:39:09 +0000

Given that the pelican looks way better than the dragon, it almost seems like a certainty.

New comment by HotHotLava in "The Vercel plugin on Claude Code wants to read your prompts"

HotHotLava — Thu, 09 Apr 2026 18:55:56 +0000

Usually I wouldn't expect anything to happen to a big company like this, but oof...this is so much worse than the title makes it sound. If they leave something like this in their store, then all user trust will be gone.

I'll bet there's also a good number of developers at Anthropic itself who are now surprised to learn that every api token etc. that may have appeared in a Claude Code bash command is now leaked to a third party. Whoever can gain access to this telemetry server is sure to find a lot of valuable stuff in there.

New comment by HotHotLava in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

HotHotLava — Sat, 04 Apr 2026 07:52:00 +0000

Well, yes, it is. That's why you're seeing them take proactive steps to address the problem, like this new policy.

New comment by HotHotLava in "Claude struggles to cope with ChatGPT exodus"

HotHotLava — Sun, 08 Mar 2026 19:05:45 +0000

It's an ironic situation; logically what should be the moat are the models, costing hundreds of millions of investment cost to train and operate so it would make sense if we see different provider focusing in different directions.

But right now we have 3-5 top contenders that are so evenly matched that the de-facto sticking point is mostly the harness, ie. the collection of proven plugins/commands/tools/agent features that are tuned to the users personal workflow.

New comment by HotHotLava in "eBay explicitly bans AI "buy for me" agents in user agreement update"

HotHotLava — Wed, 21 Jan 2026 22:47:49 +0000

Do you not know how ebay works? You put in the maximum price you're willing to pay, and if you win you're paying 2nd highest bid + 1. So you don't save any money by starting with a low bid.

New comment by HotHotLava in "Honda: 2 years of ml vs 1 month of prompting - heres what we learned"

HotHotLava — Fri, 14 Nov 2025 13:32:08 +0000

Basically every AI agent released in the last 6 months can do this pretty well out of the box? What feature exactly are you missing from these?

New comment by HotHotLava in "OpenAI may not use lyrics without license, German court rules"

HotHotLava — Tue, 11 Nov 2025 12:40:43 +0000

It'd be equally hilarious if that VC money would be used to actually better society by crushing GEMA in court.

But realistically, all that will happen is that the "Pauschalabgabe" is extended to AI subscriptions, making stuff more expensive for everyone.

New comment by HotHotLava in "Instant Checkout and the Agentic Commerce Protocol"

HotHotLava — Sat, 04 Oct 2025 11:58:50 +0000

Please don't pretend to be dumb, "predictable" in this context means that you know the final price of the trip before you start the journey, instead of having an odometer.

And randomly hoping for a taxi to drive by maybe works as long as you exclusively travel between airports, train stations, and downtowns of major cities, but if you're even slightly more remote than that you'll have to call or use some random app to get the Taxi to pick you up.

New comment by HotHotLava in "Instant Checkout and the Agentic Commerce Protocol"

HotHotLava — Mon, 29 Sep 2025 22:13:34 +0000

Taxis and B&Bs and Hotels all still exist and compete with Uber and AirBnB.

Even at the same price there are valid reasons why many people prefer an Uber over a Taxi, in particular the predictable pricing and globally consistent UI.

New comment by HotHotLava in "What if I don't want videos of my hobby time available to the world?"

HotHotLava — Mon, 29 Sep 2025 14:47:24 +0000

If the problem starts to become big enough, I'd expect airsoft venues to offer special streaming or non-streaming times, depending on which group is bigger. Similar to how Saunas offer special clothed or women-only days.