Gadak
Ask a local SQLite mirror of your Jira and Confluence: SQL, full-text search, issue detail.
- Transport
- Not stated
- Package
- —
- Registry id
- io.github.midagedev/gadak
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
gadak mirrors the Jira Cloud projects and Confluence spaces you choose into one SQLite file on your machine. The page states that SQL over the same file answers counts JQL cannot express. The page says that on a live Cloud site with 3,296 issues, the epic count query took 22 ms against 4,761 ms over 8 API pages aggregated client-side.
The page says the mirror is ordinary SQLite and if gadak went away, the file opens in any SQLite client. The page states that the app has no telemetry, no analytics, and no gadak account. The page says that writes go through Jira first and the cache refreshes after Jira accepts them.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.