← Trackingplan

MCP · Claude, ChatGPT, Cursor, your IDE

Trackingplan MCP: check the data before your AI acts on it.

The Trackingplan MCP brings your tracking into Claude, ChatGPT, Cursor or your IDE: what fires, what broke, consent, and the spend from your ad accounts. Each person signs in as themselves, with no API key, and every answer shows the evidence behind it.

Start asking your data → Book a demo

Ask it

Ask it from the tool you already use

The same agent answers through the MCP: it works from your real traffic, investigates before it answers, and shows the evidence. Two threads an analyst would open from Claude or Cursor.

Thread↗
Trackingplandemo workspace
You · Analyst

What broke in my tracking this week?

open_warnings · 7danomalies · all providers · 7d
Trackingplan

Two things worth your time, nothing on fire.

1 · TikTok purchase fires twice on mobile web since v87 — inflating TikTok’s signal, GA4 unaffected.
2 · checkout_step lost coupon on web after v95 yesterday.
Everything else — 31 events, 14 providers, consent coverage — matches last week within normal variance.

2 open issues · 0 anomalies · 14 providers healthy
Continue this thread with the agentSend

Sample workspace: questions, answers and figures are illustrative. To try it on your own data, start your free trial.

Another thread↗
Trackingplandemo workspace
You · Analyst

Which campaigns lost match rate this week, and why?

event_match_quality · meta, google_ads · 7d vs previous 7dinspect_payloads · purchase · missing identifiers
Trackingplan

Alert: Meta event match quality fell from 8.1 to 5.6 on Spring Sale – Prospecting and Retargeting – Cart since Tuesday. Those two campaigns are optimizing on a thinner signal; Google Ads is unaffected.

Cause: checkout now renders the confirmation page before the user object is in the dataLayer, so em goes out empty on 61% of purchases. fbp and fbc still arrive; this is a race, not a missing field.

Fix: push user before the purchase event, or fire the Meta tag on that object. EMQ should be back above 8 within a day of the change.

meta EMQ: 8.1 → 5.6 · 61% purchases without em · google_ads OK
Continue this thread with the agentSend

Sample workspace: questions, answers and figures are illustrative. To try it on your own data, start your free trial.

In the product

What it does in your AI tool

Book a demo

Let’s see if we’re a match, data-style.

This isn’t a sales call. It’s a chance to understand what matters most to you, discuss any data quality concerns you may have, and share practical ways Trackingplan could support your goals, if it makes sense.

FAQ

About the Trackingplan MCP.

?What is the Trackingplan MCP?
tp

The MCP endpoint of your Trackingplan plan. Connect Claude, ChatGPT, Cursor or your IDE to it and you get an Ask Trackingplan tool. Behind that tool is the whole agent, with its data, its context and its standard of evidence, working from inside the assistant you already use.

?How do I connect it?
tp

Open Settings & Members > Connect, copy the plan’s MCP endpoint and add it to your tool as an HTTP MCP server. It asks you to sign in through your browser. You don’t need an API key: each person signs in with their own account. The steps are in the MCP endpoint docs.

?What can my assistant see through it?
tp

What you see in the app: the hits your sites and apps send to GA4 and 170+ other providers, the dataLayer, the consent signals, the issues Trackingplan has found and your tracking plan. If an admin has connected your ad accounts, also spend, clicks and reported conversions per campaign from eleven ad networks (see Ad Platforms).

?Can it change my plan or my campaigns?
tp

Your plan, only with your approval. You can ask it to create a draft event, delete an event with no hits in 30 days, change an event’s spec, or mute and unmute a warning; nothing changes until you approve it. It never bids or changes a campaign.

?Why not just connect my analytics platform’s own MCP server?
tp

Because an AI agent can only reason about what it can see. A platform’s server hands your assistant the numbers that platform reports, broken events included. Trackingplan adds how each number was produced, so the assistant can tell a weaker campaign from a broken tag. Use both. We compare the platforms’ servers in analytics MCP servers.

?Who can turn it off?
tp

The endpoint belongs to the plan, not to one person. If you turn it off, it closes for everyone who connects to it. All AI features in Trackingplan are optional, and plan admins can turn them on or off at any time.

More of Trackingplan