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.
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
Makes sense. Payload secrets are probably the scarier part anyway. Would a simple redact config make sense, like keys/patterns to scrub before writing traces?
"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.
16 comments
[ 4.2 ms ] story [ 129 ms ] threadIs it possible to add a simple browser page to brows the data in a simple way?. Thank you.
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