google-analytics-mcp
Eliminates manual GA4 data extraction and transformation overhead, enabling AI agents to query traffic and user behavior directly within agentic workflows wh…
Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.
- Ask Claude to identify which pages drive the most user conversions this quarter.
- Generate a traffic summary comparing mobile versus desktop user behavior trends.
- Find which traffic sources bring the highest-value customers to your website.
Eliminates manual GA4 data extraction and transformation overhead, enabling AI agents to query traffic and user behavior directly within agentic workflows while enforcing safe aggregation defaults that reduce engineering time spent on data prep.
Engineering teams and data consultants building AI-driven analytics workflows that need structured, schema-discoverable access to GA4 metrics without custom ETL.
https://github.com/surendranb/google-analytics-mcp
By surendranb
How to Get It
claude mcp add google-analytics-mcp -- npx -y google-analytics-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
Once it’s connected, paste this into Claude:
Identify which pages drive the most user conversions this quarter
Trust Signals Auto-scanned
Data & Access
Community Pulse New
- Google Analytics MCP for Claude — Hacker News · 4 pts
- Google Analytics problem - odd map of Florida — Hacker News · 1 pts
2 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 229 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 229 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.