Your revenue data, inside the AI client you already work in.
Chartsy runs a Model Context Protocol server, so your AI assistant can read your analytics itself instead of waiting for you to paste numbers into a chat. Available for Chartsy for SaaS, it points Claude at one URL - and MRR, churn, at-risk customers, revenue concentration and traffic sources become things you can simply ask about — in the same conversation where you're already reviewing code, drafting an investor update, or planning next quarter.
Asking an AI assistant about your business today means becoming its data pipeline. You open a dashboard, screenshot a chart, paste a number, then repeat it three more times when the follow-up question needs data you didn't bring. By the time the assistant has enough context to say something useful, you've done most of the analytical work yourself.
MCP removes that step entirely. The Model Context Protocol is an open standard for letting an AI client call tools on an external system — so instead of you fetching the numbers, the assistant fetches them. Ask how the business is doing and it pulls the whole snapshot itself, warning flags included.
The server exposes the same synced data your dashboards are built from, so the numbers always match what you see in Chartsy. Revenue: current MRR, MRR by plan and by country, revenue broken down by plan, country or payment method, and refund totals with refund ratio per plan. Growth and retention: new subscribers and churn rate over any date range at day, week, month, quarter or year granularity, plus progress against your active goals.
Customers: top customers by lifetime revenue, customers at risk of churning, and what share of MRR sits in your top accounts. Website analytics: visits, unique visitors and signups over time, and traffic sources with signup rate per group — by source, medium, campaign, country, referrer or landing path. And one snapshot tool that returns the lot over a single shared time window, along with derived warnings about revenue concentration, churn spikes and refund ratios.
A conversation is an easy place to leak something by accident, so the MCP surface is deliberately tighter than the product itself. Customers come back as payment-processor ids only — names and emails are never sent over MCP, and the site-analytics tools return counts with no visitor emails. If you need to know which human an id belongs to, you look it up in Chartsy.
Every tool is read-only. Nothing creates, edits or deletes anything in Chartsy, and nothing reaches back into Stripe or Paddle — the read-only connections those providers granted are not re-exposed. The worst any AI client can do with this server is read numbers you already have.
The server reads live billing data, so you need a payment provider connected and synced first. Any plan works, including the free trial.
Chartsy's server is remote and speaks streamable HTTP — nothing to install and nothing to host. In Claude, paste the server URL under Settings, Connectors, Add custom connector and sign in with your Chartsy login. In Claude Code it's a single claude mcp add command using the same OAuth flow.
Your assistant sees the tool list and picks what it needs. Broad questions resolve in one snapshot call over a single shared time window, rather than a scatter of individual metric calls that may not line up with each other.
Because the data now lives in the same conversation as everything else, you can go straight from a churn number to drafting the investor update paragraph, or from a traffic source breakdown to the decision about next month's spend.
Chartsy MCP is for Stripe- and Paddle-based SaaS founders and operators who already work inside an AI client and want their revenue data there too — reviewing metrics alongside code, drafting board and investor updates from real figures, or interrogating churn and attribution without switching tabs to a dashboard first.
Ministry of Economy and Innovation
Startup AlbaniaThe Chartsy program is realized with the financial support of the Albanian Government through the Ministry of Economy and Innovation, under the Grant 2026 scheme, and is implemented by the Innovation4Albania Agency.