Sign inGet started
Your agent (MCP)

What is an analytics MCP server?

View as MarkdownOpen in ChatGPTOpen in Claude
Connect your agent
Add to CursorAdd to VS Code

An analytics MCP server lets your agent read your site's visits and answer questions about them. What it is, what it can do and how to connect one.

Updated

An analytics MCP server is web analytics your agent reads through the Model Context Protocol (MCP). Instead of opening a dashboard, you ask Claude, Cursor or Codex "What changed on the site this week?", and the agent calls the server's tools, reads the numbers and answers with them.

nextanalytica is one: a remote MCP server at https://mcp.nextanalytica.app/mcp, with a tag that collects your site's visits.

How is it different from a dashboard?

A dashboard shows the charts someone chose in advance. An agent with an analytics MCP server asks the question you have now, follows up on its own (which page, which channel, since when) and explains the answer in a sentence. It can also read your team's goals and decisions, so the answer fits your business.

What can your agent do with it?

  • Read visits, pages, channels and conversions by day with query and get_dashboard.
  • Find what changed and why with find_changes and get_timeline.
  • Read the signals our daily rules found with list_insights.
  • Look at people and cohorts with find_people and get_person.
  • Add the tag to your site with get_tag.

Every tool is listed in the MCP tools reference.

Does it run on a schedule?

Yes. Skills are instructions your agent runs for you on a schedule, on your own Claude Code once you allow it. They write a finding only when something is worth your time. See Skills.

How do I connect one?

Add the address to your agent and sign in. In Claude Code:

claude mcp add --transport http nextanalytica https://mcp.nextanalytica.app/mcp

Other clients: Claude Desktop, Cursor, Codex and more.

Next steps

Related
  • Your agent: Connect your own agent to nextanalytica's MCP server and ask about your site in plain words, instead of reading a dashboard.
  • Use cases: Questions to ask your agent, by task, with what comes back, and multi-step recipes that build on each answer.
  • MCP tools reference: Every tool your agent can call on the nextanalytica MCP server, with its arguments and example prompts.
  • FAQ and advanced setup: What people ask before they connect an agent: cost, clients, keys, projects, where data goes and safety, answered straight.
  • Agent keys and OAuth: Two ways your agent signs in as you: the browser sign-in, or a personal agent key for a server or script with no browser, and which to use.
  • Team access: Who on your team can connect an agent to nextanalytica, what the owner, admin and member roles allow, and how a person's or a key's access ends.
Still have questions?
Was this page useful?