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 →](https://app.trackingplan.com/signup) [Book a demo](/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.

**Trackingplan** demo 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

Suggested next actions

[Fix the TikTok one first](/#ask=What%20broke%20in%20my%20tracking%20this%20week%3F) [Send both to whoever owns GTM](/#ask=What%20broke%20in%20my%20tracking%20this%20week%3F) [Send me this every Monday](/#ask=What%20broke%20in%20my%20tracking%20this%20week%3F)

[Continue this thread with the agentSend](/#ask=What%20broke%20in%20my%20tracking%20this%20week%3F)

Sample workspace: questions, answers and figures are illustrative. To try it on your own data, [start your free trial](https://app.trackingplan.com/signup).

**Trackingplan** demo 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

Suggested next actions

[Show me the hits without the email](/#ask=Which%20campaigns%20lost%20match%20rate%20this%20week%2C%20and%20why%3F) [Send this to the paid media team](/#ask=Which%20campaigns%20lost%20match%20rate%20this%20week%2C%20and%20why%3F) [Tell me when match quality moves again](/#ask=Which%20campaigns%20lost%20match%20rate%20this%20week%2C%20and%20why%3F)

[Continue this thread with the agentSend](/#ask=Which%20campaigns%20lost%20match%20rate%20this%20week%2C%20and%20why%3F)

Sample workspace: questions, answers and figures are illustrative. To try it on your own data, [start your free trial](https://app.trackingplan.com/signup).

In the product

## What it does in your AI tool

-   Connect · one address
    
    ### Copy the address. Sign in as yourself.
    
    In Settings & Members > Connect, copy your plan’s MCP endpoint and add it to Claude, ChatGPT, Cursor or your IDE as an HTTP MCP server. It asks you to sign in through your browser. No API key to share: everyone sees exactly what they see in the app.
    
    [Set up the MCP endpoint →](/docs/mcp-endpoint)
    
-   Evidence · behind every number
    
    ### The data behind the numbers, not only the numbers.
    
    A platform’s own MCP server shows your assistant the numbers that platform reports. Trackingplan shows it the data behind them: the hits your sites and apps send to GA4 and 170+ other providers, the dataLayer and the consent signals. Every answer shows the queries behind it.
    
    [Analytics MCP servers compared →](/guides/analytics-mcp-servers)
    
-   Paid media · before you move budget
    
    ### Catch the broken signal before bidding learns from it.
    
    Ask where match rate is lost, where value is missing or where CAPI double-counts, with spend, clicks and reported conversions from eleven ad networks next to the traffic. Audits check what each pixel receives and end with the fix to ask for, so the signals you send get better. It never bids or changes a campaign.
    
-   Attribution · always on
    
    ### The click IDs, event\_id and UTMs, under watch.
    
    Trackingplan keeps watching the click IDs, event\_id and UTMs that connect a conversion to its ad, on real traffic. When one goes missing after a release, you ask why from the same chat where you were reading the campaign.
    
-   Changes · with your approval
    
    ### It proposes. You approve.
    
    From your assistant you can change the plan: 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.
    

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.

[Book a demo →](/demo) [Start free trial](https://app.trackingplan.com/signup)

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](/docs/mcp-endpoint).

?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](/docs/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](/guides/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

-   [Monitoring · always on**Every hit, every hour, every event — watched.**](/landings/monitoring)
-   [Install · 30 seconds**One tag. Your entire data layer monitored.**](/landings/install)
-   [Coverage · every platform**If it leaves the browser, the app or the server, we see it.**](/landings/coverage)
-   [Schema · semantics & context**The context your AI needs, built automatically.**](/landings/schema)
-   [For performance teams**Stop bidding blind on Meta, Google, Bing and TikTok.**](/landings/paid-media)
-   [For digital analytics teams**Automate the work that consumes your analytics capacity.**](/landings/data-analyst)
-   [For privacy & legal**Catch PII leaks and consent breaches before legal does.**](/landings/privacy)
-   [Agencies & consultancies**Every client’s tracking, audited every day, without a bigger team.**](/landings/agencies)
-   [Automation**Describe it once. Runs forever.**](/landings/automations)
-   [Journey explorer · real sessions**Complete visibility into your users data, every step of the way**](/landings/journey-explorer)
-   [Monitoring · iOS, Android, backend**Always accurate mobile analytics, even as your apps evolve**](/landings/app-tracking-monitoring)
-   [For developers**Your QA engineer for the dataLayer, the SDKs and every release.**](/landings/qa)
-   [AI analytics agent · for marketing teams**An AI analytics agent that tells you why conversions dropped.**](/landings/ai-analytics-agent)
-   [Reports · written, edited, scheduled**Automated reporting for marketing, written for you to sign.**](/landings/reports)

**Chats**

×

Send

Sample workspace: questions, answers and figures are illustrative. To try it on your own data, [start your free trial](https://app.trackingplan.com/signup).
