AI agents get asked to build Excel reports constantly. When a Python-based agent gets that
request, it almost always reaches for the same library: [openpyxl](https://openpyxl.readthedocs.io/).
So I ran a real test: give the same task to (a) a generic Python/openpyxl session and (b) an
agent using [Kookerella.FsOpenXmlDsl](https://github.com/Kookerella-Ltd/Kookerella.FsOpenXmlDsl)’s
MCP server, and look at what actually landed in the resulting file - not what either session claimed it did.
Everything below is real: real code, run for real, with the resulting .xlsx
files inspected
by unzipping them (an .xlsx
is just a zip of XML parts) to check what’s objectively inside, rather than trusting either tool’s own success message.
source & further reading
kookerella.com — original article
Openpyxl silently drops cached formula values when you edit an unrelated cell
Decompiling an Excel template into a script - #4 JSON
Decompiling an Excel template into source - #1 C#