How I'm monitoring my MCP server logs (opens in new tab)

We recently built an MCP server (https://github.com/tinybirdco/mcp-tinybird/tree/main) so our users could ask questions to their workspace. We released fast and since MCP servers run locally we lacked observability on product metrics, error monitoring and all that stuff you usually want when you are in production.

Built something generic to monitor MCP servers (https://github.com/tinybirdco/mcp-tinybird/tree/main/mcp-ser...) using events + tinybird + prometheus + grafana, but I'm wondering what others are using for that purpose?

i’ve been looking at your implementation as a reference, thank you

have you run into this weird bug which causes python MCP servers to crash when the MCP client times out? https://github.com/modelcontextprotocol/python-sdk/issues/88

also generally do you have any advice for how to notify Claude Desktop when a long running tool call is done? there are resource notifications but those must be selected by the user in the subsequent message

thanks!