66 Analytics Tools Your AI Agent Didn't Know It Needed

I check my analytics dashboard maybe twice a week. Which means I miss the spike on Tuesday and the crash on Thursday, every single time. By the time I notice something interesting happened, it's three days old and the moment is gone.

This is the fundamental lie of analytics: the data is always there, but you are never looking at it when it matters.

The Dashboard Problem

Here's what kills me about analytics tools. We spend real money and real engineering hours setting them up. We add tracking scripts. We configure events. We define goals and funnels. We wire up UTM parameters across every campaign. All this effort to collect data.

Then we don't look at it.

It's not laziness. It's friction. The information exists in a place that requires context-switching. You have to leave your workflow, open a browser, authenticate, and then manually interrogate the data by clicking around. By the time you've done all that, you forgot what question you were trying to answer.

This is especially painful with Umami. I switched to it from Google Analytics about a year ago because I was tired of feeding Google my users' data. Umami is privacy-first, open-source, and genuinely pleasant to self-host. The dashboard is clean. The data is honest. But it's still a dashboard. And I still don't look at it enough.

Making Analytics Conversational

So I built umami-mcp. It's an MCP server that exposes the entire Umami API v2 as tools your AI agent can call. 66 of them.

That number isn't padding. Umami's API surface is genuinely large — website management, analytics queries, report generation, real-time monitoring, user administration, event tracking. The MCP server covers all of it.

Setup takes about thirty seconds:

{
  "mcpServers": {
    "umami": {
      "command": "npx",
      "args": ["-y", "@mikusnuz/umami-mcp"],
      "env": {
        "UMAMI_URL": "https://analytics.yourdomain.com",
        "UMAMI_USERNAME": "admin",
        "UMAMI_PASSWORD": "your-password"
      }
    }
  }
}

Point it at your Umami instance — self-hosted or Umami Cloud, doesn't matter — and your AI agent now has full read-write access to your analytics. No API keys to generate, no OAuth dance. Just your Umami credentials.

What This Actually Feels Like

The shift is subtle but significant. Instead of going to your analytics, your analytics come to you.

Me: How did the blog do last week? Anything unusual?

Claude: Looking at your blog stats for March 16-22...
    - 4,287 pageviews (up 34% from previous week)
    - Top page: "/mcp-app-store" with 1,891 views
    - Traffic spike on Tuesday — 1,203 views, mostly from Hacker News
    - Bounce rate dropped to 42% (was 58%)
    - Top referrer: news.ycombinator.com (847 sessions)
    You had a solid HN hit on Tuesday that you probably missed.

Yeah. I did miss it. I always miss it. But now I don't have to remember to check — I just ask when it crosses my mind, mid-conversation, while I'm already working on something else.

The report generation is where it gets genuinely useful. Umami supports funnel reports, retention analysis, UTM attribution, goal tracking, and revenue tracking. All of those are available as MCP tools.

Me: Build me a funnel report for the signup flow.
    Steps: landing page -> pricing page -> signup page -> dashboard.
    Last 30 days.

Claude: Creating funnel report "Signup Flow - March"...
    Step 1: /landing — 12,847 visitors
    Step 2: /pricing — 3,201 (24.9% of step 1)
    Step 3: /signup — 891 (27.8% of step 2)
    Step 4: /dashboard — 634 (71.2% of step 3)

    Overall conversion: 4.9%
    Biggest drop-off: landing to pricing (75.1% lost).
    Once people see pricing, about a quarter continue. And your
    signup-to-activation rate is actually strong at 71%.

Try getting that out of a dashboard in under five minutes. You'd be clicking through menus, configuring date ranges, adding funnel steps one by one. Here it's one sentence and you get the data plus interpretation.

The Real-Time Angle

This one changed how I think about monitoring. Umami has a real-time API, and umami-mcp exposes it. Your agent can check active visitors, current pages being viewed, and live referrer data.

The interesting move is combining this with your normal workflow. You push a new blog post, share it on Twitter, and ten minutes later you ask: "Anyone reading the new post yet?" Instead of nervously refreshing a dashboard tab, you get a quick answer and move on.

For product launches, this is even more powerful. Ask your agent to check real-time traffic periodically and flag anything unusual. Not a formal alerting system with webhook configs and threshold settings — just a conversational check-in that takes two seconds.

66 vs. 5

Most analytics MCP integrations I've seen offer maybe 5-10 tools. Get pageviews. Get top pages. Get referrers. Basic read-only stuff. That's fine for a quick glance, but it's not enough to replace the dashboard.

66 tools means you can actually stop opening the Umami UI for almost everything. Website management — create, update, delete, reset. Full analytics queries — stats, pageviews, metrics, sessions, events, with proper date ranges and filters. Report CRUD — create funnel reports, retention reports, save them, share them. User and team administration. Even batch event tracking if you're sending data programmatically.

The point isn't that any single tool is revolutionary. It's that comprehensive coverage eliminates the last excuse to open the dashboard. When your agent can do everything the UI can do, you just stop going there.

The Privacy-First Part

I should mention why Umami specifically. If you're using Google Analytics, you're sending your visitors' data to Google. You know this. You've accepted it, or you've added a cookie banner and pretended that fixes things.

Umami is self-hosted (or cloud-hosted by them, not by an ad company). No cookies. No personal data collection. GDPR-compliant by default, not by configuration. Connecting that to an MCP server means your analytics data stays in your infrastructure. The agent talks to your Umami instance directly. Nothing goes through a third party — it flows from your server to your local agent and nowhere else.

The Honest Bit

This isn't going to replace proper observability tooling. If you need PagerDuty-level alerting with escalation policies and on-call rotations, that's a different problem. This is for the 90% of analytics interactions that are just "I'm curious, show me the numbers."

The write operations — creating websites, managing users, sending events — require some trust in your agent not to do something dumb. Start with read-only use cases and work up from there. The analytics queries alone are worth the setup.

Also, Umami's API has rate limits. If you ask your agent to run twenty complex queries in rapid succession, you might hit them. Be conversational, not adversarial.

The Bottom Line

I've been running this for a few weeks now. My analytics habit went from "check dashboard twice a week, miss everything important" to "ask a question whenever I'm curious, actually know what's happening." That's it. That's the whole pitch.

66 tools. Privacy-first analytics. No more dashboard tab collecting dust in your browser.

Install it. Ask your agent how your site did yesterday. You'll be surprised what you've been missing.