AI-powered Measurement Operations for the Google analytics stack (GA4, GTM, BigQuery, Consent Mode, Server-Side, Data Quality, Alerts), over the Model Context Protocol.
Project description
📊 Measure Analytics MCP
AI-powered Measurement Operations for the Google analytics stack, over the Model Context Protocol.
A product of the Measure MCP ecosystem · built on measure-sdk.
What it is
Audit, analyse and monitor your Google analytics stack in natural language, from Claude Desktop, ChatGPT or any MCP client. Seven focused MCP servers, each consuming the shared measure-sdk (domain models, Health Score, OAuth, …):
| Server | Run with | Domain |
|---|---|---|
| BigQuery Analyst | measure-bigquery |
Cost-aware, read-only SQL. |
| GA4 Intelligence | measure-ga4 |
GA4 Admin + Data API audits. |
| Consent Mode Auditor | measure-consent |
Consent Mode v2 compliance. |
| Data Quality | measure-dataquality |
GA4-export health monitoring. |
| GTM Operations | measure-gtm |
Web container audits + guarded writes. |
| Server-Side Auditor | measure-sgtm |
sGTM config + Cloud Run health. |
| Alerts Engine | measure-alerts |
Persistent cross-domain alerts. |
Paid-media analysis (Google Ads, Meta, …) lives in the sibling product measure-paid-media-mcp.
Install
pip install measure-analytics-mcp # pulls measure-sdk automatically
measure login # Google OAuth — that's all you need
measure doctor # see what's connected
measure-bigquery # start a server (stdio)
measure login (from the SDK) caches an OAuth token locally; every server then
works with no .env and no manual IDs. ADC / service accounts still work as a
fallback. Read-only by default; writes require explicit confirmation.
Develop
git clone https://github.com/measure-mcp/measure-analytics-mcp.git
cd measure-analytics-mcp
uv sync --all-extras # resolves measure-sdk from its pinned tag
uv run ruff check . && uv run mypy . && uv run pytest
This repo is a single installable package (measure-analytics-mcp) that
ships seven focused MCP servers under src/ (measure_ga4, measure_gtm,
measure_bigquery, measure_consent, measure_sgtm, measure_dataquality,
measure_alerts). It depends only on measure-sdk.
Ecosystem
| measure-sdk | Shared core: domain models, enums, Health Score, infra. |
| measure-analytics-mcp | This product. |
| measure-paid-media-mcp | Google Ads, Meta, LinkedIn, TikTok, CM360. |
See CHANGELOG.md · ROADMAP.md · SECURITY.md · CONTRIBUTING.md.
License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file measure_analytics_mcp-0.2.0.tar.gz.
File metadata
- Download URL: measure_analytics_mcp-0.2.0.tar.gz
- Upload date:
- Size: 94.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
aba08d0014c85993463c3d20b8d867e89a949b1529f3f35761d99d77dd4f3e57
|
|
| MD5 |
9c8843bd95e170204341acb3c98ba03e
|
|
| BLAKE2b-256 |
be45d5aa71a2a701e9b787cd4b862121946e32c067942518940b24eaebe346fc
|
Provenance
The following attestation bundles were made for measure_analytics_mcp-0.2.0.tar.gz:
Publisher:
release.yml on measure-mcp/measure-analytics-mcp
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
measure_analytics_mcp-0.2.0.tar.gz -
Subject digest:
aba08d0014c85993463c3d20b8d867e89a949b1529f3f35761d99d77dd4f3e57 - Sigstore transparency entry: 2112294460
- Sigstore integration time:
-
Permalink:
measure-mcp/measure-analytics-mcp@97268e2138b1c62492866702b9189d24eacc365a -
Branch / Tag:
refs/heads/main - Owner: https://github.com/measure-mcp
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@97268e2138b1c62492866702b9189d24eacc365a -
Trigger Event:
workflow_dispatch
-
Statement type:
File details
Details for the file measure_analytics_mcp-0.2.0-py3-none-any.whl.
File metadata
- Download URL: measure_analytics_mcp-0.2.0-py3-none-any.whl
- Upload date:
- Size: 78.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b780a1e920d51faddbbffea8cc9cac0f591a0ac885540224290e643ab145d086
|
|
| MD5 |
b43ebb44113b1ebfaa2cf0ef7d0e69d9
|
|
| BLAKE2b-256 |
b41d0c8437a7f21ff6e5a730a002db6d2194e72275c8640b34df0ff3a2c90c49
|
Provenance
The following attestation bundles were made for measure_analytics_mcp-0.2.0-py3-none-any.whl:
Publisher:
release.yml on measure-mcp/measure-analytics-mcp
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
measure_analytics_mcp-0.2.0-py3-none-any.whl -
Subject digest:
b780a1e920d51faddbbffea8cc9cac0f591a0ac885540224290e643ab145d086 - Sigstore transparency entry: 2112294473
- Sigstore integration time:
-
Permalink:
measure-mcp/measure-analytics-mcp@97268e2138b1c62492866702b9189d24eacc365a -
Branch / Tag:
refs/heads/main - Owner: https://github.com/measure-mcp
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@97268e2138b1c62492866702b9189d24eacc365a -
Trigger Event:
workflow_dispatch
-
Statement type: