Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #14426

F

Formal

Company blog · joinformal.com/blogsecurityai

Formal is the company blog at joinformal.com, writing about security and ai. Since 2025, 5 different Hacker News readers have linked it 7 times, most often “Using Proxies to Hide Secrets from Claude Code”. It is still writing: the last post was on 2026-10-23, and you can follow it by feed.

Visit the blog
7mentions?
5HN people?
2025–2026first – last linked?
Links on Hacker News per year · peak 5 in 2026

Too few sampled comments (2) to say how often HN recommends it.?

Why HN links it

HN readers link this blog's posts on composing APIs and CLIs for LLMs and on giving LLMs safe SSH and database access through fine-grained credentials and proxies.

Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Control every packet your AI agents send. Formal unifies PAM, SASE, LLM gateway, and MCP gateway into one stack that enforces least privilege inline.

Most-linked posts?

  1. Using Proxies to Hide Secrets from Claude Code
    2 people · 2 mentions · first linked 2026-01-13

What Hacker News says?

  1. mbil · 2026-01-23Recommends
    thanks for sharing this, it resonates with me. as some other commenters have said, CLIs, cURL, and other shell tools are composable and discoverable. it seems like a good direction. auth considerations are present in the design of MCP. this, as opposed to the hodgepodge auth story with CLIs. there are APIs that either don't support OAuth or where using bare credentials is more expedient, and using agent-visible env…

    Comment linking /blog/using-proxies-to-hide-secrets-from-claude-code/

    on “Composing APIs and CLIs in the LLM Era”
  2. Submitted Down the rabbit hole: Implementing SSH port forwarding over AWS Session Manager as a story · 59 points

    HN discussion
  3. I am very passionate about this question - so much so that I happened make a blog post about it yesterday! I recommend giving LLMs credentials that are extremely fine-grained, where the credentials can only permit the actions you want to allow and not permit the actions you don't want to allow. Often, it may be hard or impossible to do this with your database settings alone - in that case, you can use proxies to sep…

    Comment linking /blog/allowlisting-some-bash-commands-is-often-the-same-as-allowlisting-all-with-claude-code/

    on “Ask HN: How do you safely give LLMs SSH/DB access?”
  4. Submitted Editing Code Visually Without Sacrificing Fidelity as a story · 3 points

    HN discussion
  5. Submitted The Permission Pitfall: Securing MCP Servers Without Limiting Value as a story · 2 points

    HN discussion
  6. Submitted Allowlisting Some Bash Commands Is Often the Same as Allowlisting All as a story · 1 points

    HN discussion
  7. Submitted Using Proxies to Hide Secrets from Claude Code as a story · 1 points

    HN discussion

Search all of HN for joinformal.com