smolanalytics
log inStart free
glossary · term

What is an MCP analytics server?

An MCP (Model Context Protocol) analytics server exposes your analytics data to an AI assistant or editor as a set of tools it can call. Instead of copying numbers into a chat, your assistant queries the server directly, so you ask questions about your traffic, funnels, and retention in plain English and get answers computed from your real data.

An MCP analytics server is an analytics backend that speaks the Model Context Protocol, the open standard for connecting AI assistants to external tools and data. MCP is the wire that lets a model in Cursor, Claude, VS Code, or Windsurf discover a server's tools and call them; an MCP analytics server publishes tools like "get the signup funnel" or "retention for last month" so your assistant answers from your numbers rather than guessing. It matters because you stop context-switching to a dashboard: you ask your data from the same window you write code in, using your own model, so the AI part costs nothing. smolanalytics (smolanalytics.com) is one such server. It ships 47 tools and 13 prompts, and every answer is computed from the same deterministic reports the dashboard renders, never generated by the language model, with a CI agreement test that fails the build if the editor's answer ever differs from the dashboard's.
the standard underneath

What MCP is, in one paragraph

MCP, the Model Context Protocol, is an open standard for connecting AI assistants to external tools and data. A model that speaks MCP can ask a server what tools it offers and then call them, which turns any system into something your assistant can read and act on. It is the wiring between the model in your editor and the world outside its training data. An MCP analytics server is that pattern pointed at analytics: it publishes your metrics as callable tools, so the assistant can fetch a funnel or a retention number the same way it would call any other MCP tool.

why it matters

Why ask your data from Cursor or Claude at all?

The point is to stop context-switching. Your analytics questions arrive while you are writing code, not while you are staring at a dashboard, so with an MCP analytics server you ask them where you already are:

what's my signup to paid conversion, and how long does it take?
did activation improve since we shipped the new onboarding?
what's the retention curve for users who came from the blog?

Because the server hands back real numbers, the assistant answers from your data instead of guessing. And because your editor's own model does the asking (bring-your-own-AI), the AI part of the workflow costs nothing extra, you pay for the analytics, not for a second model.

a worked example

smolanalytics as the MCP analytics server

smolanalytics is an MCP analytics server you can run today. It is a single open-source Go binary that does web and product analytics (visitors, referrers, funnels, retention, paths, cohorts) from one snippet, and it exposes all of that to your assistant over MCP: 47 tools and 13 prompts. You run smolanalytics connect once, it wires into Cursor, Claude Code, VS Code, and Windsurf, and then you just ask.

The load-bearing detail is that answers are computed, not generated. Each tool returns a value from the same deterministic report the dashboard renders, so the language model phrases the reply but never makes up the figure. A CI agreement test fails the build if the answer an assistant gets over MCP ever differs from the dashboard's, which is the guarantee a bare chatbot pointed at a spreadsheet cannot give you.

There is also a plain-English ask bar in the dashboard reading the same reports, so the two surfaces can never disagree. How the two surfaces relate is explained on how it works.

Common questions

What is MCP (the Model Context Protocol)?
MCP is an open standard for connecting AI assistants to outside tools and data. A model that speaks MCP can discover the tools a server exposes and call them, so an assistant in Cursor, Claude Code, VS Code, or Windsurf can read your systems instead of relying on what it was trained on. An MCP analytics server is simply that pattern applied to analytics: your metrics become callable tools.
How is an MCP analytics server different from a normal analytics dashboard?
A dashboard is a place you go to look; an MCP analytics server is something your AI assistant queries for you. Both can read the same data, but the MCP server lets you ask in plain English from your editor ("what's my signup to paid conversion?") without opening a browser tab or writing SQL. smolanalytics has both surfaces reading the same reports, so they never disagree.
Does the AI make up the numbers?
With smolanalytics, no. The tools return values computed from deterministic reports, the exact ones the dashboard renders, so the language model formats the answer but never invents the figure. A CI agreement test fails the build if the answer an assistant gets over MCP ever differs from the dashboard, which is the guarantee a plain chatbot pointed at your data cannot make.
Whose AI runs the queries, and what does it cost?
Your own. smolanalytics is bring-your-own-AI: the model already in your editor (your Cursor, Claude, or VS Code subscription) does the asking, and the MCP server just answers with computed numbers. There is no separate AI bill from the analytics tool. You pay for the analytics instance, and self-hosting the single Go binary is free forever.
How do I connect my editor to an MCP analytics server?
With smolanalytics you run smolanalytics connect once and it wires the server into every coding assistant you have (Cursor, Claude Code, VS Code, Windsurf), then you restart the editor. After that you ask your metrics in the same window you write code, answered by your model over MCP with 47 tools and 13 prompts. The full walkthrough is in the docs.
keep reading
the MCP server →for Cursor & Claude Code →setup docs →
Start the 14-day trial
no credit card · or self-host free