Spanly
See what AI agents do inside your MCP server
72 followers
See what AI agents do inside your MCP server
72 followers
Soon, more agents than humans will use your product via MCP. Spanly gives you full observability on the MCP server you ship: error rates, session traces, latency, client analytics, deploy alerts. Drop-in CLI or SDK. US & EU data residency. Built for SaaS engineering teams shipping MCP in production, alongside the Datadog, Sentry, or New Relic you already run.
Spanly
This is timely. I ship an MCP server, and my blind spot is tool-level, not transport. I want to see which tools agents actually reach for versus the ones I built that never get touched, plus the shape of the arguments they pass, because that would change what I cut and what I harden far more than p95 would. Are you capturing per-tool call analytics and argument patterns, or mostly session traces and latency right now?
Spanly
@hunter_upscale Hey Ahmed!
Spanly does rank tools by their number of requests, it also allows you to dig into each request and see the actual arguments and result.
Per tool call analytics: yes
Argument patterns: yes for inspection, no for generalized analytics
I love your insight for the argument "shape" analytics, will see how I can get that into the product in the coming weeks!
Thanks for the feedback, and let me know if you would have some other feature in mind that would help make your MCP better.