Birbla

Discussion summary

Mcpsnoop is a Wireshark-like tool for MCP that provides live visualization and transparency. Users discuss potential redaction of sensitive data and integration options.

What the discussion says

  • Some users suggest redacting secrets like keys before logging.
  • The tool captures JSON-RPC messages but not headers, limiting redaction.
  • There are existing MCPs for Wireshark that can be used as alternatives.
  • Adding a web interface for browsing data is considered feasible.
“Payload secrets are probably the scarier part.”
— geraldsterling
“The gap of visualization of calling the AI client is covered by your product!!”
— yr_animesh

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • One question about http mode, you carry authorization headers. Do you redact bearer tokens before captures hit the logs?
    by mmakeev
  • 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.

    by chopete3
  • This is awesome, thank you. What's missing now is an MCP for Wireshark.
    by atmanactive
  • 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.
    by tiku
  • Great. I dream to see MCP of MCP, discovery, installation, security and usage should be automatic.
    by iamgopal
  • "MCP Inspector [...] never sees the traffic between your client and your server." This line resonates a lot, what you're building makes sense to me! I had built something similar to track these interactions and turn them into a benchmark, I'm gonna try this out.
    by rstagi
  • I feel most of the comments here are from bots
    by cidd
  • 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

    by westurner

Explore Birbla archives