Analytics
Google Analytics MCP connector
The Google Analytics connector brings your accounts, properties, custom dimensions, user access and change history into Claude, ChatGPT, Cursor and any MCP client, so your team can review and tidy Google Analytics setup by asking in plain language.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
66 tools
How to connect
How to connect Google Analytics to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Google Analytics once
-
Open Connections, choose Add connection, and pick Google Analytics.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Google Analytics. Google Analytics's own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Google Analytics to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect Google Analytics to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect Google Analytics to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Google Analytics to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Google Analytics through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Marketing
Set up a property for a new site
When a campaign site or new brand goes live, create the Google Analytics property, add the custom dimensions the team needs to track, and confirm it landed in the right account, all from one conversation.
-
Analytics
Keep custom dimensions clean
Ask for every custom dimension across a property, spot the ones nobody uses or that duplicate each other, then rename what should stay and archive what should not.
-
IT
See who has access to each account
List the people bound to a Google Analytics account, pull an access report for a property, and find the ex-contractor or old agency login that should have been removed months ago.
-
Compliance
Find out who changed a setting
When a property suddenly looks different, search the change history to see who edited what and when, and get a plain summary rather than reading through the admin screens.
-
Agency
Take stock of every client account
Pull account summaries across all the Google Analytics accounts you manage, list the properties under each, and update names or settings that have drifted out of your naming standard.
-
Web
Review data sharing before launch
Before a new property goes live, check its account's data sharing settings and confirm they match what legal signed off, then fix anything that does not.
Try asking
- “Summarize last week's traffic across our GA4 properties.”
- “Which accounts have new access bindings this month?”
- “List change history for the marketing property.”
AI tools
Google Analytics tools for your AI agents
66 tools are ready to call through Elaichi's MCP endpoint the moment you connect Google Analytics, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Google Analytics gets you
6 screens from the product, each doing one job for your Google Analytics account.
The agent
Ask about properties, get answers from live reports.
Type a question in plain language and read it back from Google Analytics.
- accounts
- properties
- access bindings
- reports
Ask Elaichi to work across your apps.
Summarize last week's traffic across our GA4 properties.
Which accounts have new access bindings this month?
List change history for the marketing property.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor share one endpoint.
Connect any MCP client over OAuth, with no SDK and no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
66 Google Analytics tools, no custom code.
Browse accounts, properties, access bindings and change history by tool name, resource and method.
- List all Google Analytics accounts
- Get single Google Analytics account by ID
- List all Google Analytics account user
- List all Google Analytics accounts alpha
ElaichiToolsToolboxes
Every team gets its own toolbox.
Growth, marketing and finance each see a curated set of Google Analytics tools.
- Growth
- Marketing
- Web
- Data
ElaichiToolboxesShared connections
Teammates use accounts without seeing credentials.
Each connection shows who added it and which teams and members share it.
- Growth
- Marketing EMEA
- Web platform
- Data engineering
ElaichiConnectionsAudit log
Answer who ran which report, and when.
Every Google Analytics call is logged with actor, event, type and resource.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule fires, a digest posts back.
Six steps fetch and group properties, draft a digest, then wait for approval.
Google Analytics digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch accounts
Google Analytics
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Google Analytics
Queued
Collections and dashboards
Property health numbers, computed on a schedule.
Four metrics, 14 days of reports created and a breakdown by team.
Google Analytics health
Refreshed 4 minutes ago · every 15 minutes · from the accounts collection
Accounts
1,284 ↓ 12%
Properties
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Accounts created
Last 14 days
By team
Share of activity
Growth 34%
Marketing EMEA 27%
Web platform 21%
Data engineering 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect Google Analytics to Claude?
Connect Google Analytics in Elaichi first: you sign in with your Google account and approve access, the same way you would sign in to Google Analytics itself. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude asks you to sign in to Elaichi, and Google Analytics is ready to use.
Does Google Analytics work with ChatGPT and Cursor as well as Claude?
Yes. Once Google Analytics is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Google Analytics once and every client you use picks it up.
What can an AI agent actually do with my Google Analytics data?
With Google Analytics connected, an agent can list your accounts and properties, create or rename a property, add, update or archive custom dimensions, show who has access to an account, review data sharing settings, and search the change history to explain who changed what. Because Google Analytics has a large set of actions, short concrete asks like "archive the unused dimensions on the store property" work better than long paragraphs.
Does connecting Google Analytics give the AI access to every account and property?
No. The agent sees exactly the Google Analytics accounts and properties the signed-in person can already see, with the same viewer, editor or administrator level Google has given them. Elaichi can narrow that further, for example to read-only or to a single team's properties, but it can never widen it beyond what the person holds in Google Analytics.
Can I stop an agent from deleting or changing things in Google Analytics?
Yes. Restrictions in Elaichi apply per action, so you can allow listing accounts and properties while blocking property deletion, dimension archiving or any update. A blocked action is never shown to Claude, ChatGPT or any other client at all, so no prompt, however worded, can reach it in Google Analytics.
What happens to a Google Analytics connection when someone leaves?
When you offboard a person in Elaichi their access to Google Analytics through Elaichi ends immediately, in every client they had set up. If the Google Analytics connection was shared with a team, it keeps working for everyone else. If you disconnect Google Analytics in Elaichi entirely, it disappears from Claude, ChatGPT, Cursor and every other client at once.
Put Google Analytics in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.