Atotalnoob's comments

On: Ask HN: How are you productively using Claude code?

[Atotalnoob]

Could you share your mcp configuration? I am having trouble getting GitHub copilot to work with mcp.

[jameshiew → Atotalnoob]

This is my `mcp.json` in VS Code (requires `uvx` and `npx` to be available):

  {
   "servers": {
    "context7": {
     "command": "npx",
     "args": [
      "-y",
      "@upstash/context7-mcp"
     ],
     "type": "stdio"
    },
    "fetch": {
     "command": "uvx",
     "args": [
      "mcp-server-fetch"
     ],
     "type": "stdio"
    },
    "git": {
     "command": "uvx",
     "args": [
      "mcp-server-git"
     ],
     "type": "stdio"
    },
    "playwright": {
     "command": "npx",
     "args": [
      "@playwright/mcp@latest"
     ],
     "type": "stdio"
    },
    "brave-search": {
     "command": "npx",
     "args": [
      "-y",
      "@modelcontextprotocol/server-brave-search"
     ],
     "env": {
      "BRAVE_API_KEY": "${input:brave-api-key}"
     },
     "type": "stdio"
    }
   },
   "inputs": [
    {
     "type": "promptString",
     "id": "brave-api-key",
     "description": "Brave Data for AI API Key",
     "password": true
    }
   ]
  }

The Sonnet 4 agent usually defaults to using `fetch` for getting webpages, but I've seen it sometimes try playwright on it's own. It seems the brave-search MCP server is deprecated now, so actually it's probably not the best option as a search MCP (you also need to sign up for an API key), right now it works well though!

On: Fine dining restaurants researching guests to make their dinner unforgettable

[Atotalnoob]

The restaurants at this tier aren’t giving anyone bad service.

Service is a big component of being a Michelin starred restaurant.

On: New Date("wtf") – How well do you know JavaScript's Date class?

[Atotalnoob]

Normally, I would agree with you, but if you are going to say it’s the best language, then the criticism is fair.

Best language would be the entire ecosystem, including standard library

[teaearlgraycold → Atotalnoob]

Yes, I just think you’ve got the wrong expectations if you say “TS failed to fix half of JS’s” problems.

On: Grok 4 Launch [video]

[Atotalnoob]

Disable JavaScript or log into GitHub

On: Grok 4

[Atotalnoob]

I logged in and it started working

On: Jane Street barred from Indian markets as regulator freezes $566M

[Atotalnoob]

164k isn’t enough to buy a home in SF.

[BobaFloutist → Atotalnoob]

starting pay.

Also, it's 164k a year, not ever. So whether or not it can buy a home in SF kind of depends on how long and how fast you save.

On: Meta invests $14.3B in Scale AI to kick-start superintelligence lab

[Atotalnoob]

Isn’t that why they are paying scale?

On: I read all of Cloudflare's Claude-generated commits

[Atotalnoob]

LLMs CAN be deterministic. You can control the temperature to get the same output repeatedly.

Although I don’t really understand why you’d only want to store prompts…

What if that model is no longer available?

[saagarjha → Atotalnoob]

They’re typically not, since they typically rely on operators that aren’t (e.g. atomics).

On: From OpenAPI spec to MCP: How we built Xata's MCP server

[Atotalnoob]

The MCP attacks are really just due to bad token scoping.

If you allow Y to do X, if an attacker takes control of Y, of course they can do X.

[rexer → Atotalnoob]

I think this downplays the security issue. It's true that scoping the token correctly would prevent this exploit, but it's not a reasonable solution under the assumptions that are taken by the designers of MCP. LLM+MCP is intended to be ultra flexible, and requiring a new (differently scoped) token for each input is not flexible.

Perhaps you could have an allow/deny popup whenever the LLM wanted to interact with a service. But I think the end state there is presenting the user a bunch of metadata about the operation, which the user then needs to reason about. I don't know that's much better; those OAuth prompts are generally click throughs for users.

[wild_egg → Atotalnoob]

Can you elaborate on "bad token scoping"?

I don't think your XY phrasing fully describes the GitHub MCP exploit and curious if you think that's somehow a "token scoping" issue.

[fkyoureadthedoc → wild_egg]

I'm unaware of the GitHub MCP "exploit", but given the overall state of LLM/MCP security FUD, there's probably some self promotion blog post from a security company about an LLM doing something stupid with GitHub data that the owner of the LLM using system didn't intend.

For example, let's say I create an application that lets you chat with my open source repo. I set up my LLM with a GitHub tool. I don't want to think about oauth and getting a token from the end user, so I give it a PAT that I generated from my account. I'm even more lazy so I just used a PAT I already had laying around, and it unfortunately had read/write access to SSH keys. The user can add their ssh key to my account and do malicious things.

Oh no, MCP is super vulnerable, please buy my LLM security product.

If you give the LLM a tool, and you give the LLM input from a user, the user has access to that tool. That shrimple.

[wild_egg → fkyoureadthedoc]

https://news.ycombinator.com/item?id=44097390

Also currently on the front page. It's mainly that this tool hits the trifecta of having privileged access, untrusted inputs, and ability to exfiltrate. Most tools only do 1-2 of those so attacks need to be more sophisticated to coordinate that.

On: “ZLinq”, a Zero-Allocation LINQ Library for .NET

[Atotalnoob]

It passes all of the tests for dotnets implementation of linq….

Seems pretty bug free for a first version.