The Abacum MCP now covers your full data pipeline. Your AI assistant can query the data that feeds your models, in both its raw and processed versions, and read the complete calculation logic behind any model.

✨ What's new

Your AI assistant can now see your datasets. Ask "Did last month's NetSuite data come in correctly, and how was it classified?" and it lists your datasets with their source, last sync time, and row counts, compares the raw data against the processed version, and queries either one directly. Data quality checks that used to mean digging through loads now take one question.

It can also read your model logic. Ask it to explain a model, and it sees every formula, how variables connect, and how each one aggregates. Ask it to review a model, and it can spot improvement opportunities grounded in the actual calculation logic, not guesses.

📈 Impact

• Close-day data checks — confirm a sync landed and see how it was classified, in seconds
• Model documentation — get any model explained variable by variable, on demand
• Model reviews — improvement suggestions based on the real formulas behind your numbers

⚙️ How it works

The same query engine that powers the rest of the Abacum MCP. Your data is loaded into a fast engine on our side, and the AI runs targeted queries against it, receiving only the rows it asked for. Everything stays read-only and scoped to your Abacum permissions: Super Admins see all datasets and models; Admins see only what's shared with them.

🚀 Roll-out

Live for all organizations with MCP enabled. If your AI assistant was already connected, disconnect and reconnect the Abacum connector to pick up the new tools.