Model Context Protocol
Dashboards that build themselves--because MCP can see the warehouse.
Most "talk to your data" products hide a prompt behind a chat box. Coeleste exposes a real MCP server: a warehouse guide that teaches the model the schema, a governed metric registry, and read-only query tools. Claude, ChatGPT, Cursor, and the in-app assistant all speak the same protocol against the same lake.
The loop
- You ask: "Show MRR by product for the last 12 months, and who is about to churn."
- The model calls
warehouse.guide, thenmetrics.list, then a read-only query. - Coeleste runs the SQL. Not the model. The database.
- Tiles slam onto a board. Each one carries the query. Save it. Revise it. Pin it.
- Tomorrow, an agent asks the same board over MCP and gets the same number.
Why MCP, not a proprietary chat
A proprietary chat dies with the vendor. MCP is how the rest of the AI stack already wants to talk to tools. If your team lives in Claude or Cursor, Coeleste is already a tool they can add. If they live in the UI, the same tools run there. One permission model. One warehouse. No second source of truth.
The number is never invented
This is the architectural line. An executive at a reference deployment nearly killed a dashboard program because he believed "AI makes the numbers up." He was not wrong about the category. He is wrong about Coeleste. Known KPIs are deterministic SQL. Novel questions go through MCP with an inspectable query. If the query is wrong, you see it.
What you plug in
MCP is only as good as the lake behind it. Coeleste connects finance (Stripe, FreshBooks, QuickBooks, Xero), CRM (HubSpot, GoHighLevel), meetings (Krisp, Fathom, Fireflies), collaboration (Slack, Teams, Microsoft 365), and the MSP stack (ConnectWise, Halo, NinjaOne) into one governed picture. That is the AI BI story. MCP is how you drive it.
Coeleste is coming soon. Get early access if you want MCP dashboards on a warehouse you can actually trust.