9 comments

  • tomkow 1 minute ago
    DANG'S DAD IS A GREEDY NYC JEWISH LANDLORD WHO LOVES EVICTIONS.

    DANG IS A FAT JEW WHO LOVES CENSORSHIP.

    LETS TAKE THE INTERNET BACK FROM THESE AUTHORITARIAN FUCKHEADS!!!

    FUCK THEM! HAPPY 4TH OF JULY!!!!! FUCK EUROPE. FUCK CANADA. PUSSIES!

    GO HOME JEWS!!! YOU SUCK AT RUNNING AN ECONOMY - YOU ARE TERRIBLE AT NEWS AND INFORMATION. GO BACK TO YOUR PEDO HELL HOLES YOU UGLY STINKY JEWS! NO ONE LIKES YOU

    WE AMERICANS LIKE PROSPERITY, BEER, BLONDES, AND BIG FUCKIN TITTIES! GO HOME NOBODY WANTS YOUR TRASH ANYMORE

  • tiku 1 hour ago
    To be fair, it is really simple to build your own proxy. I built a custom authentication layer with logging and limits for Dify MCP with just 2 prompts in Kimi. Later built it out with database limts etc.
  • cidd 1 hour ago
    I feel most of the comments here are from bots
    • kerlenton 1 hour ago
      Maybe, but I didn't do it. Perhaps people are boosting their karma?
  • chopete3 2 hours ago
    This is awesome. Your comparison make it easy. This approach makes perfect sense to give 100% visibility into the back and forth.

    Is it possible to add a simple browser page to brows the data in a simple way?. Thank you.

    • kerlenton 1 hour ago
      Thank you! Showing the data in a web page should definitely be possible. But I’m not sure if this matches the original idea I had, where the tool would run in the terminal only. Why do you feel the need to show the data in a web page? Is there anything missing in the CLI?
  • yr_animesh 1 hour ago
    Its really a great tool. The gap of visualization of calling the AI client is covered by your product!!
  • iamgopal 1 hour ago
    Great. I dream to see MCP of MCP, discovery, installation, security and usage should be automatic.
  • westurner 1 hour ago
    Remote debugging and post-mortem debugging support might be useful.

    There are many AI auditability proxies;

    awesome-auditable-ai: "A curated list of papers, tools, datasets, benchmarks, and standards for building, evaluating, and auditing reliable AI agents" https://github.com/yzhao062/awesome-auditable-ai

    Aegis and LiteLLM, for example, are pre-execution firewalls that add a cryptographic audit trail. https://github.com/Justin0504/aegis

  • atmanactive 3 hours ago
    This is awesome, thank you. What's missing now is an MCP for Wireshark.
  • kerlenton 4 hours ago
    [flagged]