Hi everyone!
I’ve been working on an independent open-source project called PMM MCP Server, which connects Percona Monitoring and Management to AI assistants through the Model Context Protocol (MCP).
The idea is simple: make it easier to explore PMM monitoring data, query performance, and database health using natural-language questions.
The project currently includes:
-
Support for PMM 2.x and 3.x
-
PromQL metrics queries
-
Query Analytics (QAN) access
-
MySQL, PostgreSQL, and MongoDB monitoring information
-
Alerts and dashboard discovery
-
Read-only operation by default
It’s written in Python, licensed under MIT, and available on GitHub:
I’m sharing it here because I’d really appreciate feedback from people who use PMM regularly, especially on API compatibility, security, and additional use cases worth supporting.
This is an independent community project, not an official Percona integration.
Thanks for taking a look! I’d be happy to hear any suggestions, feedback, or criticism.
P.S. I wasn’t entirely sure which forum category would be the most appropriate for sharing a community project like this. My apologies if I’ve posted it in the wrong section. Please feel free to move the topic to a more suitable category.