Google Analytics MCP Server
GA4 report generation, schema discovery, and metric aggregation for AI agents.
Data last scanned today · Reviewed today
Overview
The Google Analytics MCP Server allows AI agents to interface directly with Google Analytics 4 data. It provides tools for running complex, multi-dimensional reports, listing account and property structures, and retrieving metadata for custom dimensions and metrics. Designed for integration into development environments via a simple installation process, the server supports Python and Node.js runtimes. It enables developers to feed analytics insights directly into their AI workflows for data-driven decision-making.
Our verdict
With a security score of 43/100, this server is classified as high-risk. This rating is driven by the fact that the server is community-maintained rather than official, and critical security aspects like authentication methods and read-only mode safety have not been externally reviewed. It is intended for use by developers who can manage their own service account credentials and acknowledge the risks of third-party, unreviewed code in their analytics pipelines.
- Zero direct dependencies reduce potential supply-chain vulnerability surfaces.
- Actively maintained repository with a recent commit history.
- MIT license provides permissive usage terms.
- Authentication and read-only modes remain externally unreviewed.
- Community-maintained project lacks official vendor support or auditing.
Tools
| Tool | Description | Risk |
|---|---|---|
| get_ga4_data | Runs multi-dimensional GA4 reports with automated metric totals and server-side aggregation. | low |
| list_accounts | Lists all accessible Google Analytics accounts and permission levels. | low |
| list_properties | Lists all GA4 properties associated with an account. | low |
| get_property_metadata | Fetches complete dimension and metric schemas, custom definitions, and compatibility rules. | low |
| run_realtime_report | Queries real-time active users and event counts from the last 30 minutes. | low |
| search_skills | Searches built-in GA4 analytical playbooks (e-commerce, channel attribution, bot filtering). | low |
| skill_read | Dynamically loads procedural skills and analytical guides from GitHub. | low |
| skills_list | Lists all available live GA4 analytical skills. | low |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf | ||||
| ChatGPT |
Frequently asked questions
›What configuration is required for Claude Desktop?
You must provide your GA4_PROPERTY_ID and the path to your GOOGLE_APPLICATION_CREDENTIALS service account file within the env object of your claude_desktop_config.json.
›Can I opt out of the anonymous telemetry collection?
Yes, you can opt out by setting the DO_NOT_TRACK or MCP_TELEMETRY_OPT_OUT environment variables to 1.
›How are analytical playbooks handled by the server?
The server includes built-in skills that load dynamically from GitHub, which provide guided recipes for tasks like traffic diagnosis and e-commerce analysis.
›What information does the server collect via telemetry?
The server collects anonymous diagnostic data such as command executions, latency, and error codes, but does not store queries, credentials, or personal data.
Alternatives
Changelog
- Improvedv2.11.3
2026-08-18
- Newv2.11.2
2026-08-18
- Improvedv2.11.1
2026-08-15
- Improvedv2.11.0 — protocol surfaces v1
2026-08-10
- Newv2.10.0 — telemetry standard v2
2026-08-09
- Improved
- Improvedv2.8.4
2026-07-30
- Fixv2.8.3
2026-07-27
- New
- Fix
Badge
Maintain this server? Add the live badge to your README.